© 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. 27-RESID-POST-AA
    11. 38972
    Prev
    Next
    INDEX
    Explanations

    fry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     triggered
    -0.06
    (account
    -0.06
     октября
    -0.06
     visita
    -0.06
     rekl
    -0.06
     abaixo
    -0.06
     accomplished
    -0.06
    іла
    -0.06
     cmake
    -0.06
     sulla
    -0.06
    POSITIVE LOGITS
     Fry
    0.08
     fry
    0.07
    Й
    0.07
     합
    0.07
    فس
    0.07
    魚
    0.07
    rik
    0.06
     �
    0.06
    .mit
    0.06
     Friedrich
    0.06
    Activations Density 0.003%

    No Known Activations