© 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. 93350
    Prev
    Next
    INDEX
    Explanations

    references to website URLs and publication details

    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
     culture
    -0.06
    arak
    -0.06
     Hancock
    -0.06
    ã
    -0.06
     barn
    -0.06
    onom
    -0.06
    olesterol
    -0.05
    BS
    -0.05
     Culture
    -0.05
    off
    -0.05
    POSITIVE LOGITS
    HEST
    0.08
     analyst
    0.07
    _DM
    0.07
    utsch
    0.07
     DbType
    0.07
     graphite
    0.07
    .synthetic
    0.07
    .dispatcher
    0.07
    Sector
    0.07
    _________________↵↵
    0.07
    Activations Density 0.002%

    No Known Activations