© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 83380
    Prev
    Next
    INDEX
    Explanations

    Shiny reactive values (R)

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     healing
    -0.07
     kok
    -0.06
    ±
    -0.06
    ราย
    -0.06
     характеристи
    -0.06
    _chi
    -0.06
     İmparator
    -0.06
    oogle
    -0.06
    이자
    -0.06
     gridBagConstraints
    -0.06
    POSITIVE LOGITS
    (word
    0.07
    EDURE
    0.07
    orpion
    0.06
    _dw
    0.06
    ries
    0.06
     lighting
    0.06
     Sweet
    0.06
    сім
    0.06
     van
    0.06
     Plaintiff
    0.06
    Activations Density 0.000%

    No Known Activations