© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16003
    Prev
    Next
    INDEX
    Explanations

    numerical data and references pertaining to medical and academic studies

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Shepard
    -0.06
    avid
    -0.06
    ovice
    -0.06
     Shir
    -0.06
    usk
    -0.06
    .shared
    -0.06
    uchos
    -0.06
    itis
    -0.05
    luet
    -0.05
    ilton
    -0.05
    POSITIVE LOGITS
    ãģıãģł
    0.07
    acimiento
    0.07
    ิà¸ĩห
    0.07
    964
    0.06
    ãĥªãĥ³ãĤ°
    0.06
     biri
    0.06
    oji
    0.06
    ucu
    0.06
    niejs
    0.06
     lá»iji
    0.06
    Activations Density 0.007%

    No Known Activations