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. 11446
    Prev
    Next
    INDEX
    Explanations

    references to specific exhibitions and their thematic elements in art

    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
    hev
    -0.07
    šov
    -0.07
    naissance
    -0.06
    endar
    -0.06
    ournaments
    -0.06
    ÏĦομα
    -0.06
    zew
    -0.06
    ofday
    -0.06
    esel
    -0.06
    umbledore
    -0.06
    POSITIVE LOGITS
     viewer
    0.11
     works
    0.11
     exhibition
    0.11
     work
    0.10
     exhibited
    0.10
     piece
    0.09
     title
    0.09
     exhibit
    0.09
     show
    0.09
     titles
    0.09
    Activations Density 0.070%

    No Known Activations