© 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. 13107
    Prev
    Next
    INDEX
    Explanations

    Affirmations

    np_max-act · gemini-2.0-flash

    This neuron picks up on short confirming or affirmative response phrases (e.g. “Yes,” “That’s correct,” etc.).

    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
    istance
    -0.07
    (pl
    -0.07
     compiling
    -0.06
    (last
    -0.06
    Our
    -0.06
     occupation
    -0.06
    _sets
    -0.06
     Completed
    -0.06
    (nx
    -0.06
     QU
    -0.06
    POSITIVE LOGITS
     순간
    0.06
     lungs
    0.06
    /umd
    0.06
     cer
    0.06
     reflex
    0.06
    ;charset
    0.06
    prisingly
    0.06
     Modify
    0.06
    ันท
    0.06
    ollah
    0.06
    Activations Density 0.024%

    No Known Activations