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. 21731
    Prev
    Next
    INDEX
    Explanations

    stage

    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
     sư
    -0.07
     Name
    -0.06
    (array
    -0.06
    овани
    -0.06
    様
    -0.06
    ingu
    -0.06
    data
    -0.06
    /R
    -0.06
    .tick
    -0.06
    setSize
    -0.06
    POSITIVE LOGITS
    мель
    0.07
    scanner
    0.06
    _browser
    0.06
     LOC
    0.06
    �p
    0.06
    _SRV
    0.06
    lacağı
    0.06
    �
    0.06
     airy
    0.06
    .Screen
    0.06
    Activations Density 0.424%

    No Known Activations