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. 81132
    Prev
    Next
    INDEX
    Explanations

    forum discussions

    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
    _gen
    -0.07
     ACCESS
    -0.07
     你
    -0.07
    库
    -0.07
     Dark
    -0.07
    cot
    -0.07
    ###
    -0.07
    internal
    -0.06
    Routes
    -0.06
     themes
    -0.06
    POSITIVE LOGITS
    五月
    0.06
    ίζ
    0.06
     DAN
    0.06
     cigaret
    0.06
    ever
    0.06
    VERTISE
    0.06
    =re
    0.06
    �
    0.06
     abundant
    0.06
    =min
    0.06
    Activations Density 0.020%

    No Known Activations