© 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. 117526
    Prev
    Next
    INDEX
    Explanations

    references to specific classic car racing activities and events

    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
    zcze
    -0.06
    -Dec
    -0.06
     industrial
    -0.06
    å·¥æ¥Ń
    -0.06
     célib
    -0.06
     automat
    -0.06
    ertino
    -0.06
    rob
    -0.06
    543
    -0.06
    alary
    -0.06
    POSITIVE LOGITS
    TEX
    0.07
    Å¡en
    0.06
    performance
    0.06
     performance
    0.06
    arend
    0.06
     road
    0.06
     parade
    0.06
    Performance
    0.06
    lep
    0.06
    jure
    0.06
    Activations Density 0.017%

    No Known Activations