© 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. 3542
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and identifiers

    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
    legs
    -0.07
    YP
    -0.07
    YPE
    -0.07
    YPES
    -0.06
    lesi
    -0.06
    kaar
    -0.06
    ungle
    -0.06
    rop
    -0.06
    rosse
    -0.06
     sna
    -0.06
    POSITIVE LOGITS
    ovit
    0.07
    ÄĽnÃŃ
    0.06
    uito
    0.06
    次
    0.06
    ีà¹ī
    0.06
     pale
    0.06
    .sk
    0.06
    offer
    0.06
     Pale
    0.06
    Altern
    0.06
    Activations Density 0.001%

    No Known Activations