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. 81211
    Prev
    Next
    INDEX
    Explanations

    place

    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
     concludes
    -0.07
     xo
    -0.07
     noble
    -0.07
     Shadow
    -0.06
     tabs
    -0.06
     quoted
    -0.06
     apolog
    -0.06
    ieres
    -0.06
     improving
    -0.06
     returned
    -0.06
    POSITIVE LOGITS
     lonely
    0.06
     Readonly
    0.06
    gear
    0.06
    .rl
    0.06
    alculate
    0.06
     Dys
    0.06
     AMAZ
    0.06
    ایند
    0.06
    _dy
    0.06
    codegen
    0.06
    Activations Density 0.022%

    No Known Activations