© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54022
    Prev
    Next
    INDEX
    Explanations

    voice

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of an “inner voice” or similar self-talk references.

    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
     Cocoa
    -0.08
    oggles
    -0.08
     breakfast
    -0.07
     saint
    -0.07
     Promo
    -0.07
     딸
    -0.06
    "){↵
    -0.06
     pumped
    -0.06
    ));
↵
↵
    -0.06
     minimum
    -0.06
    POSITIVE LOGITS
    VML
    0.07
     startPos
    0.06
    llib
    0.06
     обла
    0.06
     století
    0.06
    fte
    0.06
     thanh
    0.06
    mai
    0.06
     �
    0.06
    RequestParam
    0.06
    Activations Density 0.008%

    No Known Activations