© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128642
    Prev
    Next
    INDEX
    Explanations

    default

    np_max-act · gemini-2.0-flash

    This neuron detects the “default” token in Maven build log entries (e.g. the “default-cli” plugin‐execution marker).

    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
    ate
    -0.07
     doma
    -0.07
    apk
    -0.06
    社會
    -0.06
     copyrighted
    -0.06
     buurt
    -0.06
    Day
    -0.06
    .StackTrace
    -0.06
    	sys
    -0.06
    Alert
    -0.06
    POSITIVE LOGITS
     quant
    0.07
     twink
    0.07
    截
    0.06
    arella
    0.06
    -----------*/↵
    0.06
    gien
    0.06
     Discount
    0.06
    coach
    0.06
     Dresses
    0.06
    ственная
    0.06
    Activations Density 0.049%

    No Known Activations