© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 109137
    Prev
    Next
    INDEX
    Explanations

    bracket

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens in code (especially CSS/JS) – i.e. it detects numbers and decimal values.

    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
    言って
    -0.06
     sexkontakte
    -0.06
     kindness
    -0.06
     derail
    -0.06
     Briggs
    -0.06
     Vegetable
    -0.06
     Significant
    -0.06
    ickest
    -0.06
     dítě
    -0.05
     pedigree
    -0.05
    POSITIVE LOGITS
     $↵
    0.07
    CAF
    0.07
    afe
    0.07
    AW
    0.07
     الغ
    0.07
     LIST
    0.07
    gün
    0.06
    _OVER
    0.06
     mak
    0.06
     Ath
    0.06
    Activations Density 0.006%

    No Known Activations