© 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. 74876
    Prev
    Next
    INDEX
    Explanations

    references to individual characteristics or attributes

    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
     menace
    -0.07
    à¥ģह
    -0.07
     hob
    -0.07
    ziel
    -0.07
    locker
    -0.06
    elman
    -0.06
     duy
    -0.06
    deen
    -0.06
     Heath
    -0.06
     grav
    -0.06
    POSITIVE LOGITS
     corresponding
    0.09
     Ä°ÅŁte
    0.07
     bgColor
    0.07
    å¨ĺ
    0.07
    CEEDED
    0.06
    ///<
    0.06
    ANNER
    0.06
    TERM
    0.06
     corres
    0.06
     PackageManager
    0.06
    Activations Density 0.038%

    No Known Activations