© 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. 118333
    Prev
    Next
    INDEX
    Explanations

    .easy

    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
     Soup
    -0.06
     au
    -0.06
     saved
    -0.06
     CLASS
    -0.06
    ارج
    -0.06
     shoved
    -0.06
    TestingModule
    -0.06
    immers
    -0.06
    άνα
    -0.06
     cả
    -0.05
    POSITIVE LOGITS
    typically
    0.07
     signifies
    0.07
     carbohydr
    0.07
     hostility
    0.07
     harc
    0.06
    ocratic
    0.06
    received
    0.06
     withhold
    0.06
     worse
    0.06
     أغسطس
    0.06
    Activations Density 0.000%

    No Known Activations