© 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. 38590
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and basic sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The ending of a complete thought or paragraph in informal writing, typically ending with a period, often before transitioning to a new topic.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     OMG
    -0.08
    incerely
    -0.07
    ÙĬÙĦÙĬ
    -0.06
     Gee
    -0.06
    .DropTable
    -0.06
     AVC
    -0.06
    pectrum
    -0.06
    ãĥ³ãĥĩ
    -0.06
    thro
    -0.06
    .cloudflare
    -0.06
    POSITIVE LOGITS
    sst
    0.07
    agh
    0.06
    羣æĺ¯
    0.06
     nice
    0.06
    ibling
    0.06
    sis
    0.06
    unner
    0.06
     perfect
    0.06
    imar
    0.06
     pity
    0.06
    Activations Density 0.154%

    No Known Activations