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. 123006
    Prev
    Next
    INDEX
    Explanations

    G

    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
    收
    -0.06
     Saturdays
    -0.06
    CLASS
    -0.06
    ktion
    -0.06
     wie
    -0.06
    اند
    -0.06
    Channel
    -0.06
    илися
    -0.06
    Meta
    -0.06
    건
    -0.06
    POSITIVE LOGITS
    LANG
    0.07
     seçim
    0.07
    +"/"+
    0.07
     Cavs
    0.06
    .getTag
    0.06
     index
    0.06
    lse
    0.06
    :.:
    0.06
    _tab
    0.06
     Daytona
    0.06
    Activations Density 0.123%

    No Known Activations