© 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. 121428
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript code structures

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    erif
    -0.07
    ellig
    -0.07
     Quarter
    -0.07
    κÏĦη
    -0.06
    uche
    -0.06
    ocu
    -0.06
    uckles
    -0.06
    imat
    -0.06
    áze
    -0.06
    _HAL
    -0.06
    POSITIVE LOGITS
    Lint
    0.06
    sed
    0.06
     yacc
    0.06
    áš
    0.05
    ircuit
    0.05
    £i
    0.05
    Leaks
    0.05
    lef
    0.05
    DTD
    0.05
    hue
    0.05
    Activations Density 0.001%

    No Known Activations