© 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. 92023
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    This neuron detects the asterisk markers (“*”) used in legal case citations (the star pagination symbol before page numbers).

    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
    Joy
    -0.07
     cos
    -0.06
     OBS
    -0.06
     SEP
    -0.06
     UT
    -0.06
    apol
    -0.06
     joyful
    -0.05
     Joy
    -0.05
     (){↵
    -0.05
     quicker
    -0.05
    POSITIVE LOGITS
     دام
    0.07
    conto
    0.07
     AndAlso
    0.07
     fabricated
    0.07
     Scores
    0.07
    .tolist
    0.06
     {[%
    0.06
     truths
    0.06
    _campaign
    0.06
    _xlabel
    0.06
    Activations Density 0.002%

    No Known Activations