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. 15-RESID-POST-AA
    6. 54179
    Prev
    Next
    INDEX
    Explanations

    1

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \Factory
    -0.07
     �
    -0.07
     bei
    -0.07
     volunt
    -0.06
    _JOB
    -0.06
     geen
    -0.06
    getMockBuilder
    -0.06
    (UInt
    -0.06
     руки
    -0.06
     Ink
    -0.06
    POSITIVE LOGITS
    )[
    0.06
     apartheid
    0.06
    ators
    0.06
    طع
    0.06
    Ù
    0.06
     permissions
    0.06
     catalyst
    0.06
     removing
    0.06
     zombie
    0.06
    <UnityEngine
    0.06
    Activations Density 0.004%

    No Known Activations