© 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. 80495
    Prev
    Next
    INDEX
    Explanations

    names of individuals or related entities

    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
    amarin
    -0.10
    forman
    -0.09
    jez
    -0.09
    ruh
    -0.08
    openh
    -0.08
    blr
    -0.08
    itele
    -0.08
    rippling
    -0.08
    -------------</
    -0.08
    onz
    -0.08
    POSITIVE LOGITS
    uren
    0.07
    ught
    0.06
     Veg
    0.06
    ...↵
    0.05
    alker
    0.05
     Bro
    0.05
     Vel
    0.05
    eden
    0.05
     Bur
    0.05
     secret
    0.05
    Activations Density 0.018%

    No Known Activations