© 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. 18502
    Prev
    Next
    INDEX
    Explanations

    references to conferences and organized events

    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
    okoj
    -0.07
     will
    -0.07
    алов
    -0.06
     Dawson
    -0.05
    ="{!!
    -0.05
    uly
    -0.05
    anki
    -0.05
     stabil
    -0.05
     Weekly
    -0.05
    ü
    -0.05
    POSITIVE LOGITS
    让æĪij
    0.10
     myself
    0.08
    ç»ĻæĪij
    0.07
     byÅĤo
    0.07
     turnout
    0.07
    ivec
    0.07
    Æ°á»Ľng
    0.07
    _micro
    0.07
     jsem
    0.07
     thú
    0.07
    Activations Density 0.028%

    No Known Activations