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. 22-LLAMASCOPE-RES-131K
    6. 5474
    Prev
    Next
    INDEX
    Explanations

    updates and details about sports teams and events

    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
    ariat
    -0.07
     partial
    -0.07
     nghiá»ĩp
    -0.06
    uky
    -0.06
     Partial
    -0.06
    olan
    -0.06
    .LayoutStyle
    -0.06
    ÑĦоÑĢ
    -0.06
    ToWorld
    -0.06
    ÑĤен
    -0.06
    POSITIVE LOGITS
     facing
    0.23
     against
    0.21
     faced
    0.20
    against
    0.18
    Facing
    0.18
     face
    0.17
     faces
    0.17
     Facing
    0.17
     enfrent
    0.17
     Against
    0.16
    Activations Density 0.118%

    No Known Activations