© 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. 19-RESID-POST-AA
    11. 111765
    Prev
    Next
    INDEX
    Explanations

    on

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    яд
    -0.07
    rá
    -0.07
    原始
    -0.07
    unlikely
    -0.07
     Egyptians
    -0.07
     znám
    -0.06
    Unicode
    -0.06
     관
    -0.06
     başlar
    -0.06
    代理
    -0.06
    POSITIVE LOGITS
     перший
    0.06
    _ctrl
    0.06
     GRE
    0.06
    _typeDefinition
    0.06
    IA
    0.06
    璃
    0.06
    GRESS
    0.06
     stripped
    0.06
    ontvangst
    0.06
     extrav
    0.05
    Activations Density 0.045%

    No Known Activations