© 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. 15-LLAMASCOPE-RES-131K
    11. 87741
    Prev
    Next
    INDEX
    Explanations

    terms related to significant negative events and health-related conditions

    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
    coe
    -0.05
    enor
    -0.05
    uze
    -0.05
    -faced
    -0.05
    orns
    -0.05
    ised
    -0.05
     imper
    -0.05
    маÑħ
    -0.05
    IRTH
    -0.05
    alore
    -0.05
    POSITIVE LOGITS
    ABCDE
    0.07
    ”çļĦ
    0.07
    à¤¾à¤ł
    0.07
    illance
    0.07
    Encoded
    0.07
    .KeyPress
    0.07
    .Areas
    0.06
    )value
    0.06
    icha
    0.06
    ŀæĢ§
    0.06
    Activations Density 0.001%

    No Known Activations