© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 93524
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    ophysical
    -0.07
    公司
    -0.07
    CONDS
    -0.06
    概念
    -0.06
    tracks
    -0.06
     ト
    -0.06
    ิเศษ
    -0.06
     Từ
    -0.06
     phases
    -0.06
    -call
    -0.06
    POSITIVE LOGITS
    .Path
    0.06
    _nav
    0.06
     Kelley
    0.06
     gün
    0.05
     πριν
    0.05
     格
    0.05
     NPR
    0.05
     ################################################################
    0.05
    Lets
    0.05
    atee
    0.05
    Activations Density 0.071%

    No Known Activations