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. 104217
    Prev
    Next
    INDEX
    Explanations

    written text

    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
    mint
    -0.07
     yAxis
    -0.07
     Chase
    -0.06
    -effect
    -0.06
     แ
    -0.06
     collect
    -0.06
     executive
    -0.06
     bé
    -0.06
    ground
    -0.06
     Triple
    -0.06
    POSITIVE LOGITS
    »)
    0.07
     правил
    0.07
     пес
    0.07
     nous
    0.06
     pg
    0.06
     importing
    0.06
     Everyday
    0.06
     불
    0.06
    №№№№
    0.06
    Doctrine
    0.06
    Activations Density 0.069%

    No Known Activations