© 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. 54849
    Prev
    Next
    INDEX
    Explanations

    Gerald

    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
     bonds
    -0.07
     Likely
    -0.07
    مند
    -0.06
    Adjusted
    -0.06
    _plate
    -0.06
    ，都
    -0.06
    +)/
    -0.06
     Alignment
    -0.06
     BEGIN
    -0.06
     formats
    -0.06
    POSITIVE LOGITS
    YC
    0.06
     marshal
    0.06
     salad
    0.06
     joe
    0.06
     ayrıntılı
    0.06
     cereal
    0.06
     zastup
    0.06
     Gerald
    0.06
    -pres
    0.06
     πολυ
    0.06
    Activations Density 0.003%

    No Known Activations