© 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. 80587
    Prev
    Next
    INDEX
    Explanations

    references to scholarly articles or academic publications

    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
    loff
    -0.07
    arel
    -0.07
    lings
    -0.06
    ccd
    -0.06
    rette
    -0.06
    anchise
    -0.06
    ÑīÑij
    -0.06
    regar
    -0.05
    lope
    -0.05
     تÙĩ
    -0.05
    POSITIVE LOGITS
     samot
    0.08
    375
    0.08
     {}.
    0.08
    emez
    0.07
    352
    0.07
    _statuses
    0.06
    287
    0.06
     daleko
    0.06
    ngr
    0.06
    prav
    0.06
    Activations Density 0.000%

    No Known Activations