© 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. 91838
    Prev
    Next
    INDEX
    Explanations

    expressions of admiration and praise regarding weddings and photography

    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
    á»į
    -0.07
    ifton
    -0.06
    246
    -0.06
    odor
    -0.06
    astle
    -0.06
    icos
    -0.06
     Verified
    -0.06
    illard
    -0.06
    ypi
    -0.05
     Ken
    -0.05
    POSITIVE LOGITS
    ãģĹãģ¦ãģĦãģ¾ãģĻ
    0.07
    riangle
    0.07
    foreground
    0.07
     backgrounds
    0.07
     shot
    0.07
     عÙĦÙĬÙĥ
    0.06
    keh
    0.06
    Enlarge
    0.06
    IFORM
    0.06
    à¤ľà¤¹
    0.06
    Activations Density 0.008%

    No Known Activations