© 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. 15-LLAMASCOPE-RES-131K
    11. 26995
    Prev
    Next
    INDEX
    Explanations

    expressions related to physical sensations and emotional responses

    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
    dy
    -0.07
    або
    -0.06
     qreal
    -0.06
     Middle
    -0.06
    üyük
    -0.06
    dit
    -0.06
     Incorporated
    -0.06
    伸
    -0.05
    kud
    -0.05
     Transitional
    -0.05
    POSITIVE LOGITS
    interop
    0.08
    ongoose
    0.08
    704
    0.07
    ijkstra
    0.07
    orge
    0.07
    rawer
    0.07
    antages
    0.07
    å¢
    0.06
    urtles
    0.06
    ocre
    0.06
    Activations Density 0.030%

    No Known Activations