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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 104076
    Prev
    Next
    INDEX
    Explanations

    read

    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
    ertil
    -0.07
    enty
    -0.06
     membranes
    -0.06
     Patel
    -0.06
    �
    -0.06
    eral
    -0.06
    686
    -0.06
    ABCDE
    -0.06
     Cycling
    -0.06
    金属
    -0.06
    POSITIVE LOGITS
    ')->
    0.07
    Dan
    0.06
     blízk
    0.06
     apare
    0.06
    `(
    0.06
    wrapper
    0.06
     Feld
    0.06
     negoci
    0.06
     handleMessage
    0.06
     어떻게
    0.06
    Activations Density 0.012%

    No Known Activations