Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 30202
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Tu
    -0.07
    Mot
    -0.07
    -corner
    -0.06
     Burn
    -0.06
    Ratio
    -0.06
     پیشنهاد
    -0.06
     Lud
    -0.06
    Lesson
    -0.06
    ERO
    -0.06
     Tu
    -0.06
    POSITIVE LOGITS
     mijn
    0.07
     щось
    0.06
     Kaepernick
    0.06
     underage
    0.06
     بیش
    0.06
    [mid
    0.06
    (thread
    0.06
    /testing
    0.06
    .tem
    0.06
    ійс
    0.06
    Activations Density 0.012%

    No Known Activations