© 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. 556
    Prev
    Next
    INDEX
    Explanations

    early-stage cancer

    np_max-act · gemini-2.0-flash

    This neuron activates on clinical staging labels and related tumor‐stage terms (e.g. “early,” “stage I,” “T1,” numerical stage codes).

    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
     Sea
    -0.07
    herits
    -0.06
     contamin
    -0.06
     Movies
    -0.06
     linewidth
    -0.06
     pirates
    -0.06
     pop
    -0.06
     descri
    -0.06
    complex
    -0.06
    989
    -0.06
    POSITIVE LOGITS
    ypo
    0.07
     Aspect
    0.07
    切
    0.06
     فيها
    0.06
    ­
    0.06
    289
    0.06
    少
    0.06
     Thánh
    0.06
     Nike
    0.06
    这样
    0.06
    Activations Density 0.032%

    No Known Activations