© 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. 77140
    Prev
    Next
    INDEX
    Explanations

    elements of programming-related content

    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
     ↵↵
    -0.07
     Computes
    -0.07
    UserCode
    -0.07
     Gad
    -0.06
     Marin
    -0.06
     Jaw
    -0.06
    DBus
    -0.06
    uming
    -0.06
    .matcher
    -0.06
     MBA
    -0.06
    POSITIVE LOGITS
    quina
    0.07
    rosso
    0.07
     mü
    0.07
    efs
    0.07
    atrib
    0.06
    isContained
    0.06
    IRT
    0.06
    orp
    0.06
    Looper
    0.06
    antz
    0.06
    Activations Density 0.155%

    No Known Activations