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. 104193
    Prev
    Next
    INDEX
    Explanations

    Code/programming text

    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
    �
    -0.06
    ofil
    -0.06
    इ
    -0.06
    victim
    -0.06
     Queries
    -0.06
    _cust
    -0.06
    享
    -0.06
    perimental
    -0.05
    уются
    -0.05
    -export
    -0.05
    POSITIVE LOGITS
    дн
    0.07
    ymph
    0.07
     растения
    0.07
    (((
    0.06
    $return
    0.06
     Arthropoda
    0.06
     Sinn
    0.06
    Genesis
    0.06
     rozvoj
    0.06
    ,col
    0.06
    Activations Density 0.098%

    No Known Activations