© 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. 69249
    Prev
    Next
    INDEX
    Explanations

    Customer service responses

    np_max-act · gemini-2.0-flash

    phrases that express comparisons regarding intelligence between genders.

    oai_token-act-pair · gpt-4o-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
     folders
    -0.07
     >>
    -0.07
     fiance
    -0.07
     Square
    -0.07
     Folder
    -0.07
     Corner
    -0.07
    _safe
    -0.07
     provisions
    -0.07
    Folder
    -0.06
    NEWS
    -0.06
    POSITIVE LOGITS
    描
    0.06
    ีค
    0.06
     Coloring
    0.06
    dration
    0.06
    erli
    0.06
    _ylabel
    0.06
    ामग
    0.06
    äm
    0.06
     utrecht
    0.06
    ับร
    0.06
    Activations Density 0.015%

    No Known Activations