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. 43644
    Prev
    Next
    INDEX
    Explanations

    phrases indicating partial involvement or contribution

    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
     predominantly
    -0.11
     mostly
    -0.10
     primarily
    -0.10
     mainly
    -0.10
     principally
    -0.10
    mostly
    -0.09
     principalmente
    -0.08
     chiefly
    -0.08
     solely
    -0.07
     entirely
    -0.07
    POSITIVE LOGITS
     responsible
    0.08
     thanks
    0.08
     explains
    0.07
     why
    0.07
     through
    0.07
     благодаÑĢÑı
    0.07
     explaining
    0.07
     inspired
    0.07
     explain
    0.07
     spurred
    0.07
    Activations Density 0.019%

    No Known Activations