© 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. 82107
    Prev
    Next
    INDEX
    Explanations

    key terms associated with time, specifically focusing on the upcoming month

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

    Words that appear at key transition points in online article or blog content, often preceding a topic change or shift in narrative focus.

    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
    senal
    -0.07
    ruba
    -0.07
    abar
    -0.07
    ç§Ģ
    -0.07
    spath
    -0.07
    ãģ§ãģĤ
    -0.07
    isser
    -0.07
    instein
    -0.07
    รà¸ģ
    -0.07
    εξ
    -0.07
    POSITIVE LOGITS
    elter
    0.06
    rine
    0.06
     Tow
    0.05
     ante
    0.05
     immigr
    0.05
    /sources
    0.05
     pl
    0.05
    ¬
    0.05
     hon
    0.05
     inc
    0.05
    Activations Density 0.000%

    No Known Activations