© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126397
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash

    The neuron is mainly triggered by the word “one” (especially in phrases like “the one who…”).

    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
     Pvt
    -0.07
    abby
    -0.07
     Mom
    -0.07
    ูต
    -0.06
     Dad
    -0.06
    覧
    -0.06
    -hearted
    -0.06
    'я
    -0.06
    騎
    -0.06
    cade
    -0.06
    POSITIVE LOGITS
    yı
    0.06
    (parameter
    0.06
    _VARS
    0.06
    .term
    0.06
    اح
    0.06
    .dest
    0.06
    (img
    0.06
    (iv
    0.06
     nông
    0.06
     今
    0.06
    Activations Density 0.020%

    No Known Activations