© 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. 109775
    Prev
    Next
    INDEX
    Explanations

    self-introduction

    np_max-act · gemini-2.0-flash

    The neuron flags tokens related to self-introduction or profile-completion prompts (e.g. “introduce themselves,” filling out a profile, adding a picture).

    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
    outine
    -0.06
     novels
    -0.06
     hear
    -0.06
     governo
    -0.06
    vertising
    -0.06
     Hornets
    -0.06
     Fit
    -0.06
     wool
    -0.06
    Cd
    -0.06
    .writ
    -0.06
    POSITIVE LOGITS
     sincerely
    0.07
    تان
    0.07
     Barrier
    0.07
    ingredient
    0.06
     Transformer
    0.06
     uvád
    0.06
     Establish
    0.06
    бут
    0.06
    propertyName
    0.06
    ทะ
    0.06
    Activations Density 0.019%

    No Known Activations