© 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. 57636
    Prev
    Next
    INDEX
    Explanations

    time duration and frequency related terms

    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
     lifelong
    -0.07
    ess
    -0.07
    ãĥ¼ãĤ¸
    -0.06
    angel
    -0.06
    istan
    -0.06
    DrawerToggle
    -0.06
    è°
    -0.06
    heim
    -0.06
    ospace
    -0.06
    627
    -0.05
    POSITIVE LOGITS
     ago
    0.08
    erial
    0.07
    alem
    0.07
    -old
    0.07
    chen
    0.07
    asco
    0.07
    ago
    0.07
    icer
    0.06
     McA
    0.06
    tener
    0.06
    Activations Density 0.009%

    No Known Activations