© 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. 31445
    Prev
    Next
    INDEX
    Explanations

    citations or references to sources within the text

    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
    aret
    -0.08
    ligne
    -0.08
    orida
    -0.07
    LayoutPanel
    -0.07
    .readLine
    -0.07
    vetica
    -0.07
     unary
    -0.07
    راÙĨ
    -0.07
    uya
    -0.07
    azines
    -0.07
    POSITIVE LOGITS
    ož
    0.07
     Sew
    0.06
     Ange
    0.06
    alon
    0.06
    -|
    0.05
     link
    0.05
     SES
    0.05
    utor
    0.05
     Taken
    0.05
    ucer
    0.05
    Activations Density 0.001%

    No Known Activations