© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 108663
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical information

    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
    loor
    -0.06
    yla
    -0.06
    grave
    -0.06
    \model
    -0.06
    HELL
    -0.06
    adium
    -0.06
     Vera
    -0.06
    -orders
    -0.06
     provinces
    -0.06
    imony
    -0.05
    POSITIVE LOGITS
     US
    0.07
    ç¾İåľĭ
    0.07
    ç¾İåĽ½
    0.07
    _US
    0.07
    _ASSUME
    0.07
     USPS
    0.07
    cdb
    0.06
    elden
    0.06
     Americans
    0.06
    perl
    0.06
    Activations Density 0.005%

    No Known Activations