© 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. 83164
    Prev
    Next
    INDEX
    Explanations

    scientific terms and symbols related to particle physics and equations

    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
     Goodman
    -0.07
     ì¡
    -0.06
    clair
    -0.06
    prav
    -0.06
     shot
    -0.06
    .Simple
    -0.06
    éré
    -0.06
     Spect
    -0.06
    ment
    -0.06
     traff
    -0.06
    POSITIVE LOGITS
     scale
    0.07
     scales
    0.07
    TeV
    0.07
    usercontent
    0.07
    ollider
    0.07
    ifold
    0.07
    ordova
    0.06
    kola
    0.06
    å°º
    0.06
    .salary
    0.06
    Activations Density 0.134%

    No Known Activations