© 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. 9-LLAMASCOPE-RES-131K
    11. 97773
    Prev
    Next
    INDEX
    Explanations

    terms related to motorcycle racing

    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
    å¾
    -0.07
    ighting
    -0.07
    igue
    -0.06
    æ¿Ł
    -0.06
    çŃij
    -0.06
    IEL
    -0.06
    usercontent
    -0.06
    enas
    -0.06
    ãģ¤ãģij
    -0.06
    igr
    -0.06
    POSITIVE LOGITS
    folio
    0.07
     Son
    0.07
    urg
    0.06
    ecial
    0.06
    chas
    0.06
    azz
    0.06
    701
    0.06
    osphate
    0.06
    tail
    0.06
    .gov
    0.06
    Activations Density 0.000%

    No Known Activations