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. 81087
    Prev
    Next
    INDEX
    Explanations

    Supreme

    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
    60
    -0.06
    oglobin
    -0.06
    hotel
    -0.06
     darkest
    -0.06
     Fulton
    -0.06
    Hint
    -0.06
    	random
    -0.05
    false
    -0.05
     Gaussian
    -0.05
     baseball
    -0.05
    POSITIVE LOGITS
     SP
    0.07
    ечно
    0.07
    飯店
    0.07
     strained
    0.07
    ancellor
    0.06
    евой
    0.06
     bewild
    0.06
    (ast
    0.06
     manifestations
    0.06
     حداقل
    0.06
    Activations Density 0.001%

    No Known Activations