© 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. 87672
    Prev
    Next
    INDEX
    Explanations

    words related to medical or healthcare contexts

    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
    patrick
    -0.07
     Bapt
    -0.06
    ermann
    -0.06
    brush
    -0.06
    łģ
    -0.06
    .ai
    -0.06
    verages
    -0.06
    eya
    -0.06
    ubbo
    -0.06
    afe
    -0.06
    POSITIVE LOGITS
    ãĥĢãĤ¤
    0.08
    ama
    0.07
    ãģķãģ¾
    0.07
    аÑģÑģ
    0.07
     dus
    0.06
    èķ
    0.06
    PACE
    0.06
    angement
    0.06
     abort
    0.06
    445
    0.06
    Activations Density 0.000%

    No Known Activations