© 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. 126733
    Prev
    Next
    INDEX
    Explanations

    references to collections, artworks, or series related to visuals or creativity

    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
    Lists
    -0.07
    oksen
    -0.07
     Wikispecies
    -0.06
    ests
    -0.06
    /renderer
    -0.06
    CreateInfo
    -0.06
    mada
    -0.06
    lists
    -0.06
     Mai
    -0.06
    ntity
    -0.06
    POSITIVE LOGITS
     collection
    0.13
     series
    0.12
    collection
    0.11
     Collection
    0.11
    series
    0.10
    éĤ£äºĽ
    0.10
     list
    0.10
    -collection
    0.10
    -series
    0.09
    ãĤ·ãĥªãĥ¼ãĤº
    0.09
    Activations Density 0.059%

    No Known Activations