© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 19487
    Prev
    Next
    INDEX
    Explanations

    the letter 'A' and its variations in different contexts, likely reflecting attention to a specific pattern or formatting associated with the letter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the letter "A" when it appears as a standalone word or at the beginning of a proper noun or title.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    an uppercase “A” at the start of a word or as a standalone initial.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    na
    -0.25
    le
    -0.23
    mi
    -0.22
    st
    -0.19
    lu
    -0.19
    ta
    -0.18
    li
    -0.18
    nya
    -0.18
    lo
    -0.18
    va
    -0.17
    POSITIVE LOGITS
    ubre
    0.18
    eid
    0.18
    ulaire
    0.16
    ections
    0.16
     propos
    0.16
    -Sah
    0.16
    quisitions
    0.16
    ube
    0.15
    eil
    0.15
    ugin
    0.15
    Activations Density 0.174%

    No Known Activations