© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 124738
    Prev
    Next
    INDEX
    Explanations

    verbs related to changes, improvements, or adjustments in processes or systems

    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
    ãĤ¥
    -0.07
    theon
    -0.07
    lsen
    -0.06
     sexe
    -0.06
    itou
    -0.06
    ahun
    -0.06
     Moran
    -0.06
    æľĿ
    -0.06
     ilma
    -0.06
    kol
    -0.06
    POSITIVE LOGITS
    341
    0.07
    227
    0.07
    icast
    0.07
    LIKELY
    0.06
    CUS
    0.05
    303
    0.05
    izyon
    0.05
    ä¸Ģä¸ĭ
    0.05
    LPARAM
    0.05
    /autoload
    0.05
    Activations Density 0.064%

    No Known Activations