Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44101
    Prev
    Next
    INDEX
    Explanations

    terms related to conduction in various contexts, particularly in technology and materials

    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
    ÙĦت
    -0.08
    ÑĪки
    -0.08
    æ¢
    -0.07
     Verfügung
    -0.07
    ornado
    -0.07
    ahren
    -0.07
    глÑı
    -0.07
    ÑĢоÑģÑĤо
    -0.07
    HTTPRequest
    -0.07
    yaw
    -0.07
    POSITIVE LOGITS
    ductor
    0.21
    duct
    0.20
    duction
    0.19
    DUCT
    0.19
    ductive
    0.18
    conduct
    0.18
     conduct
    0.17
    uctor
    0.16
     conducting
    0.16
     Conduct
    0.16
    Activations Density 0.007%

    No Known Activations