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. 80622
    Prev
    Next
    INDEX
    Explanations

    diets

    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
     MAD
    -0.07
    _repository
    -0.07
    Descriptor
    -0.07
    parator
    -0.06
     张
    -0.06
     CAM
    -0.06
    	View
    -0.06
     pam
    -0.06
    _%
    -0.06
     shortcut
    -0.06
    POSITIVE LOGITS
     sophistication
    0.07
     трав
    0.07
     dvou
    0.06
    σμο
    0.06
    informatics
    0.06
     Showcase
    0.06
    ラス
    0.06
     товар
    0.06
     która
    0.06
    DOCTYPE
    0.06
    Activations Density 0.012%

    No Known Activations