© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 74863
    Prev
    Next
    INDEX
    Explanations

    references to books and publications related to art and exhibitions

    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
     desper
    -0.05
    aste
    -0.05
     dispos
    -0.05
     cascade
    -0.05
    Cast
    -0.05
     Banner
    -0.05
     uncon
    -0.05
     streak
    -0.05
     Independence
    -0.05
    ungan
    -0.05
    POSITIVE LOGITS
     book
    0.10
     volume
    0.09
    PROTO
    0.08
    book
    0.08
     Plates
    0.08
    -book
    0.07
     collector
    0.07
     volumes
    0.07
    folio
    0.07
    ollo
    0.07
    Activations Density 0.019%

    No Known Activations