© 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. 15-LLAMASCOPE-RES-131K
    11. 86003
    Prev
    Next
    INDEX
    Explanations

    references to diagrams and visual aids

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    References to visual aids (diagrams, charts, graphics) that complement textual information by providing visual representation or clarification of concepts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered by @lu-christina
    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
    671
    -0.07
    873
    -0.05
    ạm
    -0.05
     Hampton
    -0.05
     ÙĨب
    -0.05
    polate
    -0.05
     tangent
    -0.05
     fors
    -0.05
     MIC
    -0.05
     Terra
    -0.05
    POSITIVE LOGITS
     representation
    0.09
    Legend
    0.09
    omap
    0.08
    Representation
    0.08
    TOTYPE
    0.08
    representation
    0.08
    legend
    0.08
     legend
    0.07
     Legend
    0.07
     PROGMEM
    0.07
    Activations Density 0.044%

    No Known Activations