© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90734
    Prev
    Next
    INDEX
    Explanations

    Traditional Chinese Medicine

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “syndrome” and syndrome names (e.g. blood-heat syndrome, phlegm-dampness syndrome) in Traditional Chinese Medicine contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sø
    -0.08
    cod
    -0.07
     Pharm
    -0.07
     nameof
    -0.07
    Ч
    -0.07
     Paras
    -0.07
     스
    -0.07
     스트
    -0.07
     pharm
    -0.07
    куль
    -0.06
    POSITIVE LOGITS
     translucent
    0.07
    ISCO
    0.07
    isco
    0.07
    .xlsx
    0.07
     toto
    0.07
     boto
    0.06
     плав
    0.06
    zie
    0.06
     onde
    0.06
    .Absolute
    0.06
    Activations Density 0.005%

    No Known Activations