© 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. 30456
    Prev
    Next
    INDEX
    Explanations

    edit once, not many

    np_max-act · gemini-2.0-flash

    This neuron detects explanatory, second-person phrasing—especially “you,” “your,” and similar reader-addressing words.

    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
    TF
    -0.06
     到
    -0.06
     Paleo
    -0.06
    Ray
    -0.06
     requer
    -0.06
     MONEY
    -0.06
    accine
    -0.06
     Nick
    -0.06
    Parser
    -0.06
    Summary
    -0.06
    POSITIVE LOGITS
    [result
    0.07
    ẫ
    0.07
    場所
    0.06
     microphone
    0.06
     currentPlayer
    0.06
     preço
    0.06
    -file
    0.06
    -images
    0.06
    鞋
    0.06
    _YELLOW
    0.06
    Activations Density 0.070%

    No Known Activations