© 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 EvalsExportsAPI 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. 106709
    Prev
    Next
    INDEX
    Explanations

    mentions of acetyl or related chemical compounds

    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
    vida
    -0.06
     soc
    -0.06
     Buckley
    -0.06
    alie
    -0.06
    bucks
    -0.06
    жи
    -0.06
     gre
    -0.06
    itarian
    -0.06
    rup
    -0.06
    soc
    -0.06
    POSITIVE LOGITS
    -redux
    0.08
     kennenlernen
    0.07
    erno
    0.07
    ÑĢиз
    0.07
    oute
    0.07
    è¼ī
    0.07
    иÑĢов
    0.07
    ÑĦик
    0.07
    coration
    0.07
    corp
    0.07
    Activations Density 0.005%

    No Known Activations