© 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. 15186
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities

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

    Fragments of technical metadata, usernames, citations, or digital identifiers that appear in non-narrative portions of text documents.

    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
    ubb
    -0.08
    جÙĬ
    -0.07
    avis
    -0.07
    æħİ
    -0.07
    ptic
    -0.07
    reib
    -0.07
    urry
    -0.07
    ampus
    -0.07
    prox
    -0.07
    ahat
    -0.07
    POSITIVE LOGITS
    istrovstvÃŃ
    0.06
    .Override
    0.06
    icontrol
    0.06
    @dynamic
    0.06
     repro
    0.06
    MeasureSpec
    0.06
    elsen
    0.05
    ÙĬÙĦا
    0.05
    /documentation
    0.05
    -power
    0.05
    Activations Density 0.002%

    No Known Activations