© 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. 11-RESID-POST-AA
    11. 79502
    Prev
    Next
    INDEX
    Explanations

    Data analysis and plots

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grab
    -0.07
    izzle
    -0.06
     known
    -0.06
    Fault
    -0.06
     YA
    -0.06
    .ReadOnly
    -0.06
    420
    -0.06
    200
    -0.06
     bookmarks
    -0.05
     stressed
    -0.05
    POSITIVE LOGITS
    productId
    0.07
    ulumi
    0.07
    .Authentication
    0.07
     рах
    0.07
     hashmap
    0.06
    .kafka
    0.06
    Nib
    0.06
    -opening
    0.06
     gost
    0.06
    Complete
    0.06
    Activations Density 0.060%

    No Known Activations