© 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. 3435
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements or physical dimensions

    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
    isty
    -0.07
    etri
    -0.07
    inner
    -0.07
    ighton
    -0.07
    apl
    -0.07
    ittal
    -0.07
    argon
    -0.07
    lectic
    -0.06
    inar
    -0.06
    SG
    -0.06
    POSITIVE LOGITS
    esse
    0.07
    ï¸ı
    0.07
    ook
    0.07
     Patron
    0.07
    اÙĪÛĮ
    0.06
     m
    0.06
    cing
    0.06
     OST
    0.06
    chine
    0.06
    imoto
    0.06
    Activations Density 0.057%

    No Known Activations