© 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. 89710
    Prev
    Next
    INDEX
    Explanations

    statements indicating personal opinions or experiences

    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
    :↵↵
    -0.07
    ith
    -0.07
    ,↵↵
    -0.06
     :↵↵
    -0.06
    ),↵↵
    -0.06
    uzzi
    -0.06
     Kaplan
    -0.06
    anda
    -0.06
     Hart
    -0.05
    uder
    -0.05
    POSITIVE LOGITS
    lament
    0.08
    enie
    0.08
     eldre
    0.08
    avigate
    0.08
    poke
    0.07
    abbo
    0.07
    uffman
    0.07
     hence
    0.07
    afil
    0.07
    éĢģæĸĻçĦ¡æĸĻ
    0.07
    Activations Density 0.026%

    No Known Activations