© 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. 17-LLAMASCOPE-RES-131K
    11. 86834
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "he" in relation to events surrounding death and medical 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
    haf
    -0.08
    .timing
    -0.08
     inval
    -0.07
    ì¦Ŀ
    -0.07
    Ø´ÙĨ
    -0.07
     Timing
    -0.07
    оваÑĢи
    -0.07
    ç±
    -0.07
    ogenerated
    -0.07
    rente
    -0.07
    POSITIVE LOGITS
     initial
    0.10
     Ùħباش
    0.08
     initially
    0.08
    ward
    0.07
     completion
    0.07
     receipt
    0.07
    initial
    0.07
     consultation
    0.06
    wards
    0.06
     finish
    0.06
    Activations Density 0.110%

    No Known Activations