© 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. 57345
    Prev
    Next
    INDEX
    Explanations

    terminology and concepts related to data analysis and restaurant performance metrics

    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
    μά
    -0.08
     rall
    -0.08
    afc
    -0.07
    imler
    -0.07
    mesinin
    -0.07
    elapsed
    -0.07
    ayı
    -0.07
     jadx
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.07
    mpz
    -0.07
    POSITIVE LOGITS
    archive
    0.06
     during
    0.06
    utherford
    0.06
    aki
    0.06
     since
    0.06
     where
    0.06
    Archive
    0.06
     days
    0.06
    imes
    0.05
    {'
    0.05
    Activations Density 0.004%

    No Known Activations