© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 78453
    Prev
    Next
    INDEX
    Explanations

    BMW

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     civ
    -0.07
     закон
    -0.07
    alle
    -0.07
     hiç
    -0.07
     pro
    -0.06
     Tale
    -0.06
     استفاده
    -0.06
     Kab
    -0.06
     lục
    -0.06
    _regs
    -0.06
    POSITIVE LOGITS
     BMW
    0.19
    BMW
    0.17
    TM
    0.07
     �
    0.07
    csv
    0.06
    notations
    0.06
    .concurrent
    0.06
    ('|
    0.06
    〈
    0.06
    .enum
    0.06
    Activations Density 0.001%

    No Known Activations