© 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. 10954
    Prev
    Next
    INDEX
    Explanations

    which

    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
     replaces
    -0.07
    Characteristic
    -0.07
     clit
    -0.07
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    -0.06
     سلام
    -0.06
    .getNode
    -0.06
    -mini
    -0.06
     Sul
    -0.06
    <Data
    -0.06
     зависимости
    -0.06
    POSITIVE LOGITS
    oň
    0.07
    ordon
    0.07
     Angelo
    0.07
     قص
    0.07
     تصميم
    0.06
     reinforces
    0.06
     Thrones
    0.06
    02
    0.06
    489
    0.06
    ees
    0.06
    Activations Density 0.000%

    No Known Activations