© 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. 84575
    Prev
    Next
    INDEX
    Explanations

    references to collections and categorization of items

    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
    han
    -0.06
    resh
    -0.06
     st
    -0.06
     certain
    -0.06
     Garn
    -0.06
     Kad
    -0.06
     each
    -0.05
    /trunk
    -0.05
     kad
    -0.05
    Archive
    -0.05
    POSITIVE LOGITS
    eyi
    0.09
    fragment
    0.07
    peq
    0.07
    hti
    0.07
    redd
    0.07
     phot
    0.07
    AGMENT
    0.07
    rede
    0.07
    調
    0.07
     вклад
    0.07
    Activations Density 0.005%

    No Known Activations