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. 75831
    Prev
    Next
    INDEX
    Explanations

    properties

    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
     wan
    -0.07
     accompagn
    -0.06
    sequence
    -0.06
     AUT
    -0.06
     Herman
    -0.06
    ﻟ�
    -0.06
     берем
    -0.06
    فران
    -0.06
    _ag
    -0.06
     상담
    -0.06
    POSITIVE LOGITS
     properties
    0.09
    etimes
    0.07
    =======
    0.07
    .RES
    0.07
     iets
    0.07
    apply
    0.06
     Properties
    0.06
     thumbs
    0.06
    .bio
    0.06
    illions
    0.06
    Activations Density 0.012%

    No Known Activations