Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 16206
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash

    Russian names

    np_max-act-logits · gemini-2.5-flashTriggered by @johnny

    Russian names

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @johnny

    Russian names, culture

    np_max-act-logits · gemini-2.0-flashTriggered by @johnny
    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
    ades
    -0.07
    बर
    -0.07
    objc
    -0.07
     jal
    -0.07
     PhoneNumber
    -0.07
     tabela
    -0.06
    autoload
    -0.06
    �
    -0.06
     getch
    -0.06
    بیر
    -0.06
    POSITIVE LOGITS
     Pat
    0.06
    $_['
    0.06
     torment
    0.06
    (SE
    0.06
     California
    0.06
    (samples
    0.06
     Cork
    0.06
     boj
    0.06
    InputChange
    0.06
     Diameter
    0.06
    Activations Density 0.030%

    No Known Activations