© 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. 29-LLAMASCOPE-RES-32K
    11. 5175
    Prev
    Next
    INDEX
    Explanations

    names and significant events related to historical or literary figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ******************************************************************************↵
    -0.15
    çĪ½
    -0.14
    yonel
    -0.14
    eza
    -0.14
    üml
    -0.14
     strtol
    -0.13
    .opensource
    -0.13
    piel
    -0.13
    jax
    -0.13
    hiba
    -0.13
    POSITIVE LOGITS
     Great
    1.39
    Great
    1.25
     great
    1.22
     GREAT
    1.14
    great
    1.10
     ÐĴели
    0.76
     greatness
    0.62
     grande
    0.60
    reat
    0.58
     вели
    0.57
    Activations Density 0.273%

    No Known Activations