© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 9408
    Prev
    Next
    INDEX
    Explanations

    form input fields

    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
    Suffix
    -0.07
     elucid
    -0.06
    Truth
    -0.06
     шт
    -0.06
     masturbation
    -0.06
    obble
    -0.06
     Grove
    -0.06
     symbol
    -0.06
    Sq
    -0.06
    kes
    -0.06
    POSITIVE LOGITS
     YY
    0.07
     efficient
    0.07
    이지
    0.07
     publisher
    0.07
     PIO
    0.07
     olmuş
    0.06
     TNT
    0.06
    /Resources
    0.06
    ngör
    0.06
     предпол
    0.06
    Activations Density 0.008%

    No Known Activations