© 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. 72442
    Prev
    Next
    INDEX
    Explanations

    actions and events in a baseball game

    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
    æ¬ł
    -0.07
    perm
    -0.07
    asser
    -0.06
    ÏĦÏİ
    -0.06
    reate
    -0.06
    临
    -0.06
     superf
    -0.06
    perf
    -0.06
    hoff
    -0.06
    -gnu
    -0.06
    POSITIVE LOGITS
     bel
    0.06
     tub
    0.06
    追
    0.06
     Mud
    0.06
     exce
    0.06
     ÑģÑĦ
    0.06
     dispatch
    0.06
    تب
    0.06
    arl
    0.06
    arms
    0.06
    Activations Density 0.009%

    No Known Activations