© 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. 116680
    Prev
    Next
    INDEX
    Explanations

    elements related to database queries and commands

    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
    è²¼
    -0.07
    amu
    -0.06
     sider
    -0.06
    elu
    -0.06
    jing
    -0.06
     ÎĶη
    -0.06
     dripping
    -0.06
    ovit
    -0.06
    ington
    -0.06
    apest
    -0.06
    POSITIVE LOGITS
    CharacterSet
    0.07
    irst
    0.07
    gua
    0.07
     Lawson
    0.07
    ncmp
    0.07
     Kimberly
    0.07
    ecs
    0.07
    ÑĨвеÑĤ
    0.06
     Fernando
    0.06
    semblies
    0.06
    Activations Density 0.034%

    No Known Activations