© 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. 7-RESID-POST-AA
    6. 28085
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation

    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
     日本
    -0.07
     IMDb
    -0.06
     віднов
    -0.06
     �
    -0.06
    027
    -0.06
    Descricao
    -0.06
     slož
    -0.06
    找
    -0.06
    -SA
    -0.06
    DC
    -0.06
    POSITIVE LOGITS
     يع
    0.07
    READ
    0.06
    ensch
    0.06
     eql
    0.06
     jit
    0.06
    <iostream
    0.06
     Named
    0.06
    coach
    0.06
     наруш
    0.06
     cán
    0.06
    Activations Density 0.147%

    No Known Activations