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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 30823
    Prev
    Next
    INDEX
    Explanations

    code comments and annotations in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quist
    -0.15
    vie
    -0.15
    ATHER
    -0.14
    .
    -0.14
    ynos
    -0.14
     ens
    -0.14
     resid
    -0.13
     result
    -0.13
    quarters
    -0.13
     prompt
    -0.13
    POSITIVE LOGITS
    var
    0.24
    inheritdoc
    0.24
    covers
    0.23
    SuppressWarnings
    0.22
    internal
    0.22
    todo
    0.22
    uses
    0.22
    author
    0.22
    phan
    0.20
    licence
    0.20
    Activations Density 0.005%

    No Known Activations