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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23-RESID-POST-AA
    11. 65517
    Prev
    Next
    INDEX
    Explanations

    mac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zd
    -0.06
    jde
    -0.06
     sidelines
    -0.06
     Gujarat
    -0.06
     thieves
    -0.06
     internet
    -0.06
    _reserve
    -0.06
     restroom
    -0.06
     Schmidt
    -0.06
     množ
    -0.06
    POSITIVE LOGITS
    Analysis
    0.07
    _$_
    0.07
     passion
    0.06
     basil
    0.06
     Indones
    0.06
     terrific
    0.06
    模式
    0.06
    Base
    0.06
     Fluent
    0.06
    --------↵↵
    0.06
    Activations Density 0.004%

    No Known Activations