© 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. 34157
    Prev
    Next
    INDEX
    Explanations

    favorite

    np_max-act · gemini-2.0-flash

    The neuron detects expressions of personal preference—especially “my favorite” (or “favourite”) and similar first-person endorsements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    personal expressions of preference and sentiment related to experiences and favorite activities.

    oai_token-act-pair · gpt-4o-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
     계약
    -0.07
    OrElse
    -0.07
    TokenType
    -0.07
    _adapter
    -0.07
     Symptoms
    -0.06
    <Value
    -0.06
    tadır
    -0.06
     imageNamed
    -0.06
    sole
    -0.06
    Mary
    -0.06
    POSITIVE LOGITS
    modal
    0.07
    snake
    0.07
     arch
    0.06
    --[
    0.06
     инструмент
    0.06
    please
    0.06
     đích
    0.06
     zaman
    0.06
    lie
    0.06
    ْر
    0.06
    Activations Density 0.031%

    No Known Activations