© 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. 7-RESID-POST-AA
    11. 27087
    Prev
    Next
    INDEX
    Explanations

    bleach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     querying
    -0.07
    750
    -0.07
    -0.07
     Cooperation
    -0.07
    SO
    -0.07
    ILLISECONDS
    -0.07
    -0.06
     fist
    -0.06
    adt
    -0.06
    URT
    -0.06
    POSITIVE LOGITS
     bleach
    0.14
     ble
    0.09
     Ble
    0.09
    aminer
    0.07
     mí
    0.06
     Believe
    0.06
    liable
    0.06
     leak
    0.06
     stimulate
    0.06
    ละ
    0.06
    Activations Density 0.002%

    No Known Activations