© 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 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. 17-LLAMASCOPE-RES-131K
    11. 71201
    Prev
    Next
    INDEX
    Explanations

    musical chart rankings and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    565
    -0.06
    lew
    -0.06
    levard
    -0.06
    gil
    -0.06
     Garn
    -0.06
    zew
    -0.06
     McGu
    -0.06
     esk
    -0.06
    ói
    -0.06
    editor
    -0.06
    POSITIVE LOGITS
    kre
    0.08
     position
    0.08
    sel
    0.07
    ç¿Ķ
    0.06
     spot
    0.06
    yles
    0.06
     åĺ
    0.06
     -----------------------------------------------------------------------------↵
    0.06
     ellipt
    0.06
    spot
    0.06
    Activations Density 0.005%

    No Known Activations