© 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. 84418
    Prev
    Next
    INDEX
    Explanations

    terms related to physical and emotional sensations

    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
    antan
    -0.06
     spell
    -0.06
    ben
    -0.06
     Zar
    -0.06
    uns
    -0.06
    ivet
    -0.06
    aram
    -0.06
    zar
    -0.06
    ixel
    -0.06
    obia
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    inspace
    0.07
    åĿĢ
    0.07
    acente
    0.07
     wheel
    0.07
    smarty
    0.07
    åŁ
    0.07
     Joh
    0.07
    punkt
    0.07
     Wheel
    0.07
    Activations Density 0.001%

    No Known Activations