© 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. 94896
    Prev
    Next
    INDEX
    Explanations

    references to proteins and their similarities or differences

    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
    ikat
    -0.08
    ptions
    -0.06
    ion
    -0.06
     ramp
    -0.06
     momentum
    -0.06
    orda
    -0.06
    hausen
    -0.06
    uard
    -0.06
     lasting
    -0.06
    arus
    -0.06
    POSITIVE LOGITS
    chyb
    0.08
    edes
    0.07
     evolutionary
    0.07
    members
    0.06
    кав
    0.06
    orton
    0.06
     predicted
    0.06
    ancode
    0.06
    æĻ¨
    0.06
    ẫn
    0.06
    Activations Density 0.074%

    No Known Activations