© 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. 97434
    Prev
    Next
    INDEX
    Explanations

    references to keyboard instruments and players

    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
    ë¡ľëĵľ
    -0.06
    /commons
    -0.06
    efon
    -0.06
    .grp
    -0.06
    gw
    -0.06
    ooth
    -0.06
    isco
    -0.06
     بÛĮر
    -0.06
     Democr
    -0.06
    tras
    -0.06
    POSITIVE LOGITS
    akh
    0.08
    acle
    0.07
    872
    0.07
    ians
    0.07
    ovol
    0.06
    nection
    0.06
    iyon
    0.06
    352
    0.06
    loon
    0.06
     cer
    0.06
    Activations Density 0.003%

    No Known Activations