© 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. 121578
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to mathematical operations and relationships

    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
    /her
    -0.08
    Ñĥда
    -0.08
    erson
    -0.07
    иÑĤÑĥ
    -0.07
    ãĤ«ãĥ«
    -0.07
    Kyle
    -0.07
    ãĥ¬ãĥ³
    -0.07
    ially
    -0.06
    itesse
    -0.06
    اختÛĮ
    -0.06
    POSITIVE LOGITS
    /=
    0.07
    ï¸ı
    0.07
    729
    0.06
    ledged
    0.06
    299
    0.06
    UCCEEDED
    0.06
    .DependencyInjection
    0.06
    ä¹İ
    0.06
    ETERS
    0.06
    ÏĦαι
    0.06
    Activations Density 0.109%

    No Known Activations