© 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. 17-LLAMASCOPE-RES-131K
    11. 69184
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate distance and proximity

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    usta
    -0.08
    oog
    -0.07
    upertino
    -0.07
    à¸Ļาà¸Ķ
    -0.07
    usto
    -0.07
     Mond
    -0.07
    monds
    -0.07
    weg
    -0.07
    æ¡Ī
    -0.07
    unity
    -0.07
    POSITIVE LOGITS
    .lex
    0.06
    หมà¸Ķ
    0.06
    era
    0.06
    dol
    0.06
     mah
    0.06
     vacc
    0.06
    arith
    0.05
    Å
    0.05
    696
    0.05
    ìŀĶ
    0.05
    Activations Density 0.003%

    No Known Activations