© 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. 94254
    Prev
    Next
    INDEX
    Explanations

    time durations related to medical observations or experiments

    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
    enin
    -0.06
    à¥ģव
    -0.06
     Jer
    -0.06
     Mast
    -0.05
     bore
    -0.05
     Ej
    -0.05
    /front
    -0.05
     UV
    -0.05
     mast
    -0.05
     çķ
    -0.05
    POSITIVE LOGITS
    ago
    0.08
     intervals
    0.08
     Riley
    0.08
    quo
    0.08
    ÏĥÏĦαν
    0.07
    oleon
    0.07
    -old
    0.07
    алом
    0.07
    leys
    0.07
    mouseout
    0.07
    Activations Density 0.015%

    No Known Activations