© 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. 5-LLAMASCOPE-RES-131K
    11. 126500
    Prev
    Next
    INDEX
    Explanations

    technical programming terms and events related to user interface interactions

    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
    ãn
    -0.07
     Ùħسئ
    -0.07
    Ìģt
    -0.07
    äl
    -0.07
    اÙħت
    -0.07
    erox
    -0.07
    Ú©Ùĩ
    -0.07
    ë¥´ê³ł
    -0.07
    ASC
    -0.07
    дап
    -0.07
    POSITIVE LOGITS
    OnChange
    0.06
    e
    0.06
    odata
    0.06
    a
    0.06
    ksen
    0.06
    ece
    0.06
    idle
    0.06
    endoza
    0.06
     Vital
    0.06
    resultCode
    0.06
    Activations Density 0.019%

    No Known Activations