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. 44413
    Prev
    Next
    INDEX
    Explanations

    words related to collaboration or co-creation

    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
    Ù쨴
    -0.07
     term
    -0.06
    term
    -0.06
    Term
    -0.06
    fur
    -0.06
    ZX
    -0.06
    οÏħν
    -0.06
    END
    -0.06
     Term
    -0.06
    endar
    -0.05
    POSITIVE LOGITS
    -w
    0.15
    -writing
    0.14
    -write
    0.14
    -written
    0.13
    åĨĻ
    0.13
     writer
    0.12
     writ
    0.12
     escrit
    0.12
     wrote
    0.12
    writes
    0.12
    Activations Density 0.007%

    No Known Activations