© 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. 119120
    Prev
    Next
    INDEX
    Explanations

    mentions of conversations, statements, or accounts of events

    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
    658
    -0.07
    ittel
    -0.07
    pector
    -0.07
    ÃŃcul
    -0.07
    habi
    -0.06
    quisitions
    -0.06
    zcze
    -0.06
    agnost
    -0.06
     ÙĨÙĩ
    -0.06
    ungle
    -0.06
    POSITIVE LOGITS
    deb
    0.06
     deb
    0.06
    æ·
    0.06
    oney
    0.06
    \views
    0.06
    <<(
    0.06
    Construct
    0.06
    ["$
    0.06
     Deb
    0.05
    992
    0.05
    Activations Density 0.007%

    No Known Activations