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. 75837
    Prev
    Next
    INDEX
    Explanations

    API requests

    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
     Normally
    -0.07
    aghan
    -0.07
    Normally
    -0.07
    iae
    -0.07
    BMW
    -0.07
     clipped
    -0.07
     Rider
    -0.07
    JS
    -0.06
    Root
    -0.06
    dispatcher
    -0.06
    POSITIVE LOGITS
     celebrates
    0.06
     λ
    0.06
     없는
    0.06
     (£
    0.06
    从
    0.06
     advancement
    0.06
     progressives
    0.06
     Memorial
    0.06
     seviy
    0.06
     clinic
    0.06
    Activations Density 0.022%

    No Known Activations