© 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. 9-LLAMASCOPE-RES-131K
    11. 94258
    Prev
    Next
    INDEX
    Explanations

    segments of code or mathematical constructs that involve geometric calculations and intersections

    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
    elpers
    -0.07
    ingt
    -0.06
    imals
    -0.06
    olicit
    -0.06
    bons
    -0.06
    lá
    -0.06
    ucks
    -0.06
    rys
    -0.06
    utan
    -0.06
    ãģ£ãģį
    -0.06
    POSITIVE LOGITS
    //**↵
    0.09
    //*
    0.08
    avail
    0.07
    ÙĦÛĮت
    0.07
    avaÅŁ
    0.07
    eo
    0.07
    (iOS
    0.07
    ÙĪسÛĮ
    0.07
    -REAL
    0.07
    chyb
    0.07
    Activations Density 0.057%

    No Known Activations