© 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. 118283
    Prev
    Next
    INDEX
    Explanations

    General text/code

    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
    even
    -0.07
     Statements
    -0.06
     Creates
    -0.06
    ersistence
    -0.06
     مستقیم
    -0.06
     explan
    -0.06
    obody
    -0.06
    ㎡
    -0.06
    eneral
    -0.06
     Nx
    -0.06
    POSITIVE LOGITS
     verbally
    0.07
    mong
    0.07
     Nottingham
    0.06
     obchodní
    0.06
     Ürün
    0.06
     thụ
    0.06
     전용면적
    0.06
     Strand
    0.06
    airobi
    0.06
     defects
    0.06
    Activations Density 0.000%

    No Known Activations