Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19322
    Prev
    Next
    INDEX
    Explanations

    ail

    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
     Region
    -0.07
     mez
    -0.07
     speak
    -0.07
     MIX
    -0.07
     groups
    -0.07
    精品
    -0.07
     Boston
    -0.07
     West
    -0.06
    West
    -0.06
     Gods
    -0.06
    POSITIVE LOGITS
     nail
    0.11
     nails
    0.09
     Nail
    0.08
     claws
    0.07
    This
    0.07
     ng
    0.07
    digital
    0.07
     intrinsic
    0.07
    itti
    0.06
     cis
    0.06
    Activations Density 0.003%

    No Known Activations