© 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. 15-LLAMASCOPE-RES-131K
    11. 86314
    Prev
    Next
    INDEX
    Explanations

    references to influential musicians and their contributions

    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
    .mix
    -0.07
     lược
    -0.07
     localVar
    -0.07
    elez
    -0.07
    orsche
    -0.07
     Fir
    -0.07
    isclosed
    -0.07
    ãĥ¼ãĥ¬
    -0.07
    riott
    -0.07
    ilib
    -0.06
    POSITIVE LOGITS
     breakthrough
    0.07
     band
    0.06
    ½
    0.06
     member
    0.06
     role
    0.06
    lav
    0.06
     group
    0.06
     breakout
    0.06
     fame
    0.06
     groupe
    0.06
    Activations Density 0.033%

    No Known Activations