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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 73243
    Prev
    Next
    INDEX
    Explanations

    which

    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_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
    ria
    -0.06
     sett
    -0.06
    bard
    -0.06
    Comp
    -0.06
     deserve
    -0.06
     cds
    -0.06
     Memories
    -0.06
    Exp
    -0.06
     civilians
    -0.06
     foods
    -0.06
    POSITIVE LOGITS
    CLLocation
    0.07
     strcpy
    0.07
    INavigationController
    0.06
     модель
    0.06
     incontri
    0.06
     maar
    0.06
    を行
    0.06
     Streams
    0.06
    ’elle
    0.06
     उसन
    0.06
    Activations Density 0.038%

    No Known Activations