© 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. 16231
    Prev
    Next
    INDEX
    Explanations

    elements related to educational materials and translations

    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
    anou
    -0.06
    çľ¼
    -0.06
     ============================================================================↵
    -0.06
    yntax
    -0.06
    .vs
    -0.06
    _PAR
    -0.06
    ascar
    -0.06
    à¸Ńว
    -0.06
     aug
    -0.06
    omu
    -0.06
    POSITIVE LOGITS
    EMA
    0.07
     myself
    0.07
    ope
    0.07
     tôi
    0.07
    ackbar
    0.07
    EDA
    0.06
    aku
    0.06
    eor
    0.06
     cross
    0.06
    amba
    0.06
    Activations Density 0.003%

    No Known Activations