© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30437
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron activates primarily on numeric tokens (e.g. version numbers, line‐number decimals, timestamps) in the text.

    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
     Planning
    -0.08
    Meeting
    -0.06
    pio
    -0.06
    OrderBy
    -0.06
    _cores
    -0.06
    _cancel
    -0.06
     pension
    -0.06
    yses
    -0.06
    ें।
    -0.06
    _pushButton
    -0.06
    POSITIVE LOGITS
    حة
    0.07
    	ds
    0.06
     high
    0.06
    	date
    0.06
     المف
    0.06
     moist
    0.06
     REC
    0.06
    広
    0.06
    .CharField
    0.06
    (java
    0.06
    Activations Density 0.004%

    No Known Activations