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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 104130
    Prev
    Next
    INDEX
    Explanations

    words related to the function and health of the heart and neurons

    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
    chw
    -0.08
    headline
    -0.07
    VOKE
    -0.07
    datagrid
    -0.07
    ombat
    -0.07
    ród
    -0.07
    landa
    -0.07
     maur
    -0.06
    EMU
    -0.06
    ób
    -0.06
    POSITIVE LOGITS
     normal
    0.08
     proper
    0.08
    proper
    0.07
     passing
    0.07
     properly
    0.07
    cy
    0.07
     function
    0.07
     res
    0.07
    icken
    0.06
     bình
    0.06
    Activations Density 0.015%

    No Known Activations