© 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. 62160
    Prev
    Next
    INDEX
    Explanations

    references to data structures and constraints 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
    ideographic
    -0.06
    io
    -0.06
    .visitMethod
    -0.06
    _abstract
    -0.06
     Erotische
    -0.06
    otten
    -0.06
    |
    -0.06
     Geile
    -0.06
     Clare
    -0.06
     erotique
    -0.06
    POSITIVE LOGITS
    /her
    0.08
    ivery
    0.07
    inke
    0.07
    ses
    0.07
     ActionTypes
    0.07
    quia
    0.07
    ccion
    0.07
    ARRANT
    0.07
    curity
    0.07
    zelf
    0.07
    Activations Density 0.047%

    No Known Activations