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. 43717
    Prev
    Next
    INDEX
    Explanations

    references to colleges and universities

    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
    ideo
    -0.08
    atus
    -0.07
    ÏįÏĢ
    -0.07
    ÑĪÑĤ
    -0.07
    RelativeTo
    -0.07
     Visitor
    -0.07
    á»ĩn
    -0.07
    adian
    -0.06
    ATUS
    -0.06
    Ñīо
    -0.06
    POSITIVE LOGITS
     students
    0.09
    -stage
    0.08
    children
    0.07
    arbeit
    0.07
     stage
    0.07
     college
    0.07
     districts
    0.06
    college
    0.06
    aston
    0.06
    /un
    0.06
    Activations Density 0.006%

    No Known Activations