© 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. 15-LLAMASCOPE-RES-131K
    11. 90455
    Prev
    Next
    INDEX
    Explanations

    regulated communication and accountability in 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
    gend
    -0.08
    uhl
    -0.07
    .must
    -0.07
    bach
    -0.07
    ipa
    -0.07
    iyim
    -0.07
    ndo
    -0.07
    ndl
    -0.07
    yš
    -0.06
    вÑĸлÑĮ
    -0.06
    POSITIVE LOGITS
     instead
    0.12
    instead
    0.09
     Instead
    0.09
     simply
    0.08
    Instead
    0.07
     would
    0.07
     or
    0.07
     perhaps
    0.07
     hätte
    0.07
     Would
    0.06
    Activations Density 0.046%

    No Known Activations