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. 80619
    Prev
    Next
    INDEX
    Explanations

    top

    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
    ьте
    -0.07
    \Requests
    -0.06
    YPES
    -0.06
    QUIT
    -0.06
    poss
    -0.06
    again
    -0.06
    Played
    -0.06
    #echo
    -0.06
    Spoiler
    -0.06
     стандарт
    -0.06
    POSITIVE LOGITS
    rup
    0.07
     průběhu
    0.07
    735
    0.07
     BLL
    0.07
    [cnt
    0.07
    ,true
    0.07
    醴
    0.06
    	editor
    0.06
     السم
    0.06
     top
    0.06
    Activations Density 0.001%

    No Known Activations