© 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. 25-LLAMASCOPE-RES-32K
    11. 32696
    Prev
    Next
    INDEX
    Explanations

    the word "would" and its variations, indicating conditionality or potentiality in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icon
    -0.15
    asje
    -0.15
    ayne
    -0.14
    abilit
    -0.14
    idon
    -0.14
    ayment
    -0.14
    ulu
    -0.14
    EFA
    -0.14
    ardi
    -0.14
    duit
    -0.14
    POSITIVE LOGITS
    nt
    0.39
     be
    0.33
    -be
    0.30
    've
    0.25
    /c
    0.24
     likely
    0.24
     like
    0.23
    ’ve
    0.23
    /is
    0.23
     not
    0.22
    Activations Density 0.157%

    No Known Activations