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. 75406
    Prev
    Next
    INDEX
    Explanations

    equality

    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
     convin
    -0.07
     quatre
    -0.07
     warrant
    -0.07
     trabaj
    -0.06
    _encrypt
    -0.06
     Clarkson
    -0.06
     chỉnh
    -0.06
    ilere
    -0.06
    进入
    -0.06
    	sig
    -0.06
    POSITIVE LOGITS
    gg
    0.06
    �
    0.06
     equal
    0.06
    DW
    0.06
     veterinary
    0.06
     avoiding
    0.06
    .Nodes
    0.06
     Raise
    0.06
    想到
    0.06
     COLORS
    0.06
    Activations Density 0.014%

    No Known Activations