© 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. 63255
    Prev
    Next
    INDEX
    Explanations

    large numbers and their significance within the context

    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
    337
    -0.06
    eres
    -0.06
    opp
    -0.06
     anything
    -0.06
    hai
    -0.06
     consulate
    -0.06
    iam
    -0.05
    271
    -0.05
    fix
    -0.05
     EVERY
    -0.05
    POSITIVE LOGITS
    AVAILABLE
    0.08
    GLOSS
    0.08
    remaining
    0.08
    ázd
    0.08
    azor
    0.07
    ason
    0.07
     remaining
    0.07
    apore
    0.07
     existing
    0.07
    ecta
    0.07
    Activations Density 0.044%

    No Known Activations