© 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. 73086
    Prev
    Next
    INDEX
    Explanations

    key accomplishments and milestones in athletic careers

    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
    tics
    -0.07
    ascar
    -0.06
     dick
    -0.06
    extras
    -0.06
    orro
    -0.06
    swagger
    -0.06
    iona
    -0.06
    ueur
    -0.06
    ovel
    -0.06
    ----------------------------------------------------------------------
    -0.06
    POSITIVE LOGITS
    undef
    0.07
     ÙĩØ´
    0.06
     won
    0.06
     clock
    0.06
     repe
    0.06
    placed
    0.06
    ITTER
    0.05
     twice
    0.05
    amide
    0.05
    year
    0.05
    Activations Density 0.031%

    No Known Activations