© 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. 44190
    Prev
    Next
    INDEX
    Explanations

    Quotation mark

    np_max-act · gemini-2.0-flash

    This neuron fires on the quoted metadata fields in the header of a gettext PO file (e.g. “Project-Id-Version: …”, “PO-Revision-Date: …”, “Last-Translator: …”, 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
     performan
    -0.07
     pumping
    -0.06
    �
    -0.06
     듯
    -0.06
    draw
    -0.06
     ト
    -0.06
    mse
    -0.06
    ics
    -0.06
     circumcision
    -0.06
     claw
    -0.06
    POSITIVE LOGITS
     другой
    0.07
    99
    0.07
    /xml
    0.07
    weights
    0.06
    	db
    0.06
     salesman
    0.06
    塔
    0.06
     yapmak
    0.06
     може
    0.06
     osobních
    0.06
    Activations Density 0.001%

    No Known Activations