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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RESID-POST-AA
    11. 123737
    Prev
    Next
    INDEX
    Explanations

    从

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     THEY
    -0.07
    ा.↵
    -0.07
    elere
    -0.06
     дво
    -0.06
    ?↵
    -0.06
    вав
    -0.06
    КИ
    -0.06
    ؟↵
    -0.06
     och
    -0.06
     طريق
    -0.06
    POSITIVE LOGITS
    ῦ
    0.06
    飛
    0.06
    ��
    0.06
     зависимости
    0.06
    reply
    0.06
     devotion
    0.06
    성이
    0.06
    em
    0.06
    -menu
    0.06
     brushed
    0.06
    Activations Density 0.132%

    No Known Activations