© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 23282
    Prev
    Next
    INDEX
    Explanations

    generic text

    np_max-act · gemini-2.0-flash

    instances of direct address to the reader, especially second-person constructions in instructional or explanatory text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     منه
    -0.07
     Qui
    -0.07
    ，被
    -0.07
    ，您
    -0.07
    Jwt
    -0.07
    (rect
    -0.06
     Germ
    -0.06
     enumeration
    -0.06
     muddy
    -0.06
     счита
    -0.06
    POSITIVE LOGITS
    (mapStateToProps
    0.06
     Méd
    0.06
    lossen
    0.06
    ыт
    0.06
    .synthetic
    0.06
    .detach
    0.06
     thuốc
    0.05
     Türk
    0.05
     proceeding
    0.05
     khỏ
    0.05
    Activations Density 0.129%

    No Known Activations