© 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. 17-LLAMASCOPE-RES-131K
    11. 5183
    Prev
    Next
    INDEX
    Explanations

    code structure elements and syntax in programming contexts

    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
    моÑģ
    -0.07
    anko
    -0.07
    tap
    -0.06
    ucci
    -0.06
     Rosenstein
    -0.06
    orting
    -0.06
    $MESS
    -0.06
     (č↵
    -0.06
    urning
    -0.05
    omba
    -0.05
    POSITIVE LOGITS
     Reese
    0.07
    лев
    0.07
    Ïģε
    0.06
    .Obj
    0.06
    _UNUSED
    0.06
    trail
    0.06
    åģľ
    0.06
    ÑĢаÑĩ
    0.06
    ượt
    0.06
    .ActionListener
    0.06
    Activations Density 0.000%

    No Known Activations