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. 5462
    Prev
    Next
    INDEX
    Explanations

    references to governing bodies and representatives

    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
    bff
    -0.07
    ossier
    -0.07
    ondo
    -0.07
    اÙģÙĩ
    -0.07
    ãģĦãģ«
    -0.07
    лой
    -0.07
    æĸ½
    -0.07
    legg
    -0.07
    amos
    -0.06
    emploi
    -0.06
    POSITIVE LOGITS
     member
    0.14
     members
    0.14
     representation
    0.13
     membership
    0.12
    members
    0.12
    member
    0.12
     represent
    0.12
     seat
    0.11
     seats
    0.11
     representing
    0.11
    Activations Density 0.060%

    No Known Activations