© 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. 54072
    Prev
    Next
    INDEX
    Explanations

    mentions of the terms related to "nab" and its variations, likely focusing on the film industry or particular narratives within it

    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
     Trident
    -0.07
    optera
    -0.06
    ropa
    -0.06
     pairwise
    -0.06
    splash
    -0.06
    ÛĮات
    -0.05
    ìĩ
    -0.05
    adier
    -0.05
    955
    -0.05
     *)((
    -0.05
    POSITIVE LOGITS
    idebar
    0.07
    itizen
    0.07
    abbo
    0.07
    urate
    0.07
    orners
    0.07
    à¸Ńห
    0.07
    ipple
    0.07
    rett
    0.07
    urve
    0.07
    ActionTypes
    0.07
    Activations Density 0.008%

    No Known Activations