© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6942
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron fires on confirmation‐style prompts—especially “Are you sure … delete …?” questions asking the user to confirm a deletion.

    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
     SHARE
    -0.07
     organize
    -0.06
    .IOException
    -0.06
    _album
    -0.06
    iete
    -0.06
    (Convert
    -0.06
     Joel
    -0.06
    ยง
    -0.06
    .rooms
    -0.06
     swap
    -0.06
    POSITIVE LOGITS
    bio
    0.07
     Vacc
    0.06
    เอก
    0.06
    ÄŸ
    0.06
     GN
    0.06
     outpost
    0.06
     Winston
    0.06
    icago
    0.06
    ением
    0.06
    arduino
    0.06
    Activations Density 0.007%

    No Known Activations