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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4961
    Prev
    Next
    INDEX
    Explanations

    web links and references to film genres or categories

    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
     sein
    -0.15
    hlas
    -0.14
     wife
    -0.14
     нег
    -0.14
     ÙĨÙģسÙĩ
    -0.14
    lád
    -0.13
    ZeroWidthSpace
    -0.13
    his
    -0.13
     his
    -0.13
    aucoup
    -0.13
    POSITIVE LOGITS
     he
    1.05
     He
    0.94
    He
    0.87
    he
    0.84
    .he
    0.74
    _he
    0.72
    -he
    0.72
     он
    0.68
     HE
    0.64
    ä»ĸ
    0.63
    Activations Density 0.148%

    No Known Activations