© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 51708
    Prev
    Next
    INDEX
    Explanations

    antiviral medications

    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
     glVertex
    -0.07
    _base
    -0.07
    561
    -0.06
     Mushroom
    -0.06
    _EPS
    -0.06
    とは
    -0.06
     �
    -0.06
    Transformer
    -0.06
     Bran
    -0.06
    opia
    -0.06
    POSITIVE LOGITS
    ending
    0.07
    <class
    0.07
     Mandarin
    0.06
     agile
    0.06
     Heidi
    0.06
     produit
    0.06
    爱
    0.06
     соверш
    0.06
     giá
    0.06
     жест
    0.06
    Activations Density 0.002%

    No Known Activations