© 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. 129686
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron specializes in picking up references to “brother” (especially in questions about the brother’s age).

    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
     finan
    -0.06
    eded
    -0.06
    áh
    -0.06
    атегор
    -0.06
     traverse
    -0.06
    ờ
    -0.06
    pawn
    -0.06
    řez
    -0.06
    فق
    -0.06
    рій
    -0.06
    POSITIVE LOGITS
     primera
    0.07
     appropriated
    0.06
    jsp
    0.06
    }-{
    0.06
     Об
    0.06
    ifik
    0.06
     adım
    0.06
     *)↵
    0.06
     liegt
    0.06
     mig
    0.06
    Activations Density 0.176%

    No Known Activations