© 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. 12277
    Prev
    Next
    INDEX
    Explanations

    technical problems/questions

    np_max-act · gemini-2.0-flash

    The neuron spotlights first-person problem statements—occurrences of “I” (or “I’m”) and nearby verbs describing what the author is trying or running into.

    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
    Blueprint
    -0.07
     DAO
    -0.06
    bjerg
    -0.06
     Apocalypse
    -0.06
    lexport
    -0.06
    Century
    -0.06
    	sem
    -0.06
    .Re
    -0.06
    Assoc
    -0.06
    apixel
    -0.06
    POSITIVE LOGITS
     لا
    0.07
    _FILENAME
    0.07
     terrorism
    0.06
     bard
    0.06
     JUST
    0.06
     theological
    0.06
     emotion
    0.06
     تا
    0.06
    ْل
    0.06
     تعمیر
    0.06
    Activations Density 0.045%

    No Known Activations