© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 79695
    Prev
    Next
    INDEX
    Explanations

    references to social and political movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation marks (especially periods and commas) appearing before conjunction words like "but," "that," "and," "as" which connect clauses or introduce new statements.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ondon
    -0.07
    966
    -0.06
    mitted
    -0.06
    IQUE
    -0.06
    ensing
    -0.06
     onError
    -0.06
     دار
    -0.05
    vá
    -0.05
    ÅĪ
    -0.05
     easily
    -0.05
    POSITIVE LOGITS
     attempts
    0.08
     Attempt
    0.08
     attempting
    0.08
     fabric
    0.08
     shouldn
    0.07
     Attempts
    0.07
    attempt
    0.07
    лиÑĪ
    0.07
    cing
    0.07
     attempted
    0.07
    Activations Density 0.047%

    No Known Activations