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. 11445
    Prev
    Next
    INDEX
    Explanations

    characters or symbols that could represent unique identifiers or specific elements in writing

    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
    nez
    -0.06
    оло
    -0.06
    iban
    -0.06
    ToStr
    -0.06
    merchant
    -0.05
    contest
    -0.05
     Bilim
    -0.05
     Inline
    -0.05
     NotificationCenter
    -0.05
    AccessType
    -0.05
    POSITIVE LOGITS
     Residential
    0.14
     residential
    0.14
     staff
    0.11
     placement
    0.11
     Child
    0.11
     placements
    0.11
     Placement
    0.10
     Resident
    0.10
     Transitional
    0.10
     residents
    0.10
    Activations Density 0.002%

    No Known Activations