© 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. 9-LLAMASCOPE-RES-131K
    11. 99130
    Prev
    Next
    INDEX
    Explanations

    HTML tags and related elements in the text

    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
     Markets
    -0.07
    جا
    -0.06
    uz
    -0.05
     Geoff
    -0.05
     Scaffold
    -0.05
    ont
    -0.05
     Accounts
    -0.05
    mdl
    -0.05
     Strand
    -0.05
    ÑĢава
    -0.05
    POSITIVE LOGITS
    rial
    0.09
    clin
    0.07
    issen
    0.07
    веÑī
    0.07
    addons
    0.07
     errorCallback
    0.07
    @qq
    0.07
    .EventQueue
    0.07
    0.07
     ;č↵
    0.07
    Activations Density 0.002%

    No Known Activations