© 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. 72343
    Prev
    Next
    INDEX
    Explanations

    elements of correspondence and communication between characters

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

    Punctuation and formatting elements that serve as section breaks or paragraph endings, often preceding new content or introducing quoted material.

    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
    nt
    -0.07
    unda
    -0.06
    ÃŃs
    -0.06
    un
    -0.06
    in
    -0.06
    renc
    -0.06
    ienda
    -0.06
    emem
    -0.06
    endir
    -0.06
    abh
    -0.06
    POSITIVE LOGITS
    ãĥĥãĥĦ
    0.07
    iaux
    0.07
    _HDR
    0.07
    éĨ´
    0.07
    PixelFormat
    0.07
    .@
    0.07
    æĭ¬
    0.07
    éĺħ读次æķ°
    0.06
    /*================================================================
    0.06
     åĽ½äº§
    0.06
    Activations Density 0.044%

    No Known Activations