Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126525
    Prev
    Next
    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash

    This neuron specifically detects the digit “8,” most prominently when it appears in the UTF-8 encoding declaration of XML headers.

    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
    αρα
    -0.07
     Polly
    -0.06
     potent
    -0.06
     According
    -0.06
    ('#
    -0.06
     "#"
    -0.06
    (show
    -0.06
     вал
    -0.06
     фіз
    -0.06
     savage
    -0.06
    POSITIVE LOGITS
     Matches
    0.07
    bitcoin
    0.07
    iteDatabase
    0.07
    	cur
    0.07
    createQueryBuilder
    0.06
    ipherals
    0.06
    rang
    0.06
    wb
    0.06
    stretch
    0.06
     mx
    0.06
    Activations Density 0.001%

    No Known Activations