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. 15-RESID-POST-AA
    6. 121657
    Prev
    Next
    INDEX
    Explanations

    crazy

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     limp
    -0.07
    [@"
    -0.06
     Mazda
    -0.06
    只要
    -0.06
     význam
    -0.06
     Speaking
    -0.06
    .ItemsSource
    -0.06
     truths
    -0.05
     iconic
    -0.05
     případ
    -0.05
    POSITIVE LOGITS
     insane
    0.08
     Crazy
    0.08
     crazy
    0.08
    legal
    0.07
     insanely
    0.07
    elem
    0.07
     harbor
    0.07
     mad
    0.07
     craz
    0.07
    mad
    0.07
    Activations Density 0.040%

    No Known Activations