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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84519
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to theoretical physics and modeling

    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
    (Source
    -0.07
     Mood
    -0.06
     íijľ
    -0.06
    328
    -0.06
     ken
    -0.06
     bid
    -0.06
    [
    -0.06
     representing
    -0.06
    ym
    -0.06
    orting
    -0.06
    POSITIVE LOGITS
     /*č↵
    0.07
    /*č↵
    0.07
    esto
    0.07
    ÃŃg
    0.07
    .hs
    0.07
    ãĤ¤ãĤº
    0.07
    esta
    0.06
    ør
    0.06
    #ac
    0.06
    rawn
    0.06
    Activations Density 0.056%

    No Known Activations