© 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. 81292
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly percentages and specific values

    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
    rippling
    -0.09
    AGON
    -0.08
    lád
    -0.07
    ULA
    -0.07
    rosso
    -0.07
     Fibonacci
    -0.07
     pert
    -0.07
    XObject
    -0.07
    ulary
    -0.07
    avin
    -0.07
    POSITIVE LOGITS
    æĹı
    0.06
     Pew
    0.06
    139
    0.06
     lit
    0.06
    541
    0.06
     answers
    0.06
    mo
    0.06
    138
    0.06
    izont
    0.05
    137
    0.05
    Activations Density 0.001%

    No Known Activations