© 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. 879
    Prev
    Next
    INDEX
    Explanations

    debris

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “debris.”

    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
    osyal
    -0.08
     Pipe
    -0.08
     sexkontakte
    -0.07
    .AspNetCore
    -0.07
     Constantin
    -0.07
     společnosti
    -0.07
    تماع
    -0.07
    <O
    -0.07
    opal
    -0.07
    eken
    -0.07
    POSITIVE LOGITS
     debris
    0.14
    bris
    0.10
     litter
    0.08
     Debt
    0.08
     rubble
    0.07
     merchandise
    0.07
    andise
    0.07
     graffiti
    0.07
     re
    0.07
     commodities
    0.07
    Activations Density 0.010%

    No Known Activations