© 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. 17-LLAMASCOPE-RES-131K
    11. 79953
    Prev
    Next
    INDEX
    Explanations

    phrases related to causes of death and health-related statistics

    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
    gan
    -0.07
    berger
    -0.07
    ninger
    -0.07
    еÑĩно
    -0.06
    ogonal
    -0.06
    dos
    -0.06
    ppy
    -0.06
    Dual
    -0.06
    afil
    -0.06
    ain
    -0.06
    POSITIVE LOGITS
     non
    0.06
     mid
    0.06
     among
    0.06
    ieri
    0.06
     PET
    0.06
    RL
    0.06
    inja
    0.06
    inia
    0.05
     downfall
    0.05
    reen
    0.05
    Activations Density 0.014%

    No Known Activations