© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12810
    Prev
    Next
    INDEX
    Explanations

    body parts

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “pituitary” (as in “pituitary gland”).

    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
    Ya
    -0.07
     UNION
    -0.07
     یا
    -0.07
    uckets
    -0.06
    requirements
    -0.06
    unny
    -0.06
     gated
    -0.06
     Administrator
    -0.06
    bucks
    -0.06
     докум
    -0.06
    POSITIVE LOGITS
     Attend
    0.06
     coronavirus
    0.06
    орі
    0.06
     раб
    0.06
     Flame
    0.06
     maintenant
    0.06
    .")]↵
    0.06
    ़ों
    0.06
    逐
    0.06
     fishes
    0.06
    Activations Density 0.031%

    No Known Activations