© 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. 17-LLAMASCOPE-RES-131K
    11. 82742
    Prev
    Next
    INDEX
    Explanations

    references to long-term health consequences and medical conditions related to injury

    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
    ucci
    -0.08
    emme
    -0.08
     pÅĻÃŃ
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.07
     Shelter
    -0.07
    amilia
    -0.07
     Sheldon
    -0.07
     Suspension
    -0.07
    iken
    -0.07
    ettes
    -0.07
    POSITIVE LOGITS
     permanently
    0.17
     permanent
    0.16
    æ°¸ä¹ħ
    0.14
    permanent
    0.13
    Permanent
    0.13
     Permanent
    0.13
     perman
    0.12
     forever
    0.11
     Forever
    0.09
     scar
    0.09
    Activations Density 0.031%

    No Known Activations