© 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. 126913
    Prev
    Next
    INDEX
    Explanations

    patterns related to asynchronous operations or signals

    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
    akter
    -0.07
    sson
    -0.06
    steller
    -0.06
    TriState
    -0.06
    639
    -0.06
    acket
    -0.06
    legg
    -0.06
    .Metro
    -0.05
    æĺŃ
    -0.05
     WaitForSeconds
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.07
    ileo
    0.07
     IID
    0.07
    ULL
    0.07
     *,↵
    0.06
    Å¡ek
    0.06
     Hind
    0.06
    .de
    0.06
     COPYRIGHT
    0.06
     SEQ
    0.06
    Activations Density 0.001%

    No Known Activations