© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127055
    Prev
    Next
    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash

    This neuron lights up on the questioner’s own attempts or self-references (first-person statements like “I have tried,” “I cannot,” “How do I…?”).

    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
    Em
    -0.07
     animals
    -0.07
     stuff
    -0.07
    Products
    -0.07
    En
    -0.07
     therapists
    -0.07
     Random
    -0.07
     handlers
    -0.06
    Martin
    -0.06
     therapist
    -0.06
    POSITIVE LOGITS
     NSMutable
    0.07
     søker
    0.07
     еди
    0.07
     "_
    0.07
     onOptionsItemSelected
    0.07
    };
↵
↵
    0.07
     dö
    0.07
    >/',
    0.06
    Eigen
    0.06
    答
    0.06
    Activations Density 0.046%

    No Known Activations