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. 80889
    Prev
    Next
    INDEX
    Explanations

    pap

    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
     Leigh
    -0.07
     Stretch
    -0.07
     Track
    -0.07
     �
    -0.07
     Dillon
    -0.07
     ench
    -0.07
     Holden
    -0.06
     Thorn
    -0.06
    اهش
    -0.06
    aliyet
    -0.06
    POSITIVE LOGITS
     pap
    0.11
     Pap
    0.10
     пап
    0.09
    Sam
    0.08
     Sam
    0.08
     bib
    0.08
     Papua
    0.08
     Samuel
    0.07
    fib
    0.07
     câu
    0.07
    Activations Density 0.018%

    No Known Activations