© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 88014
    Prev
    Next
    INDEX
    Explanations

    car accidents

    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
    при
    -0.08
    measurement
    -0.07
     gor
    -0.06
     Invent
    -0.06
    Expr
    -0.06
    PR
    -0.06
     topped
    -0.06
     forehead
    -0.06
    at
    -0.06
     crust
    -0.06
    POSITIVE LOGITS
    имости
    0.06
    affe
    0.06
    '''
    0.06
    ='
    0.06
     amid
    0.06
    _READONLY
    0.06
     chairman
    0.06
     Đ
    0.06
    사회
    0.06
     �
    0.06
    Activations Density 0.014%

    No Known Activations