© 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. 11-RESID-POST-AA
    11. 46020
    Prev
    Next
    INDEX
    Explanations

    is

    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
    frame
    -0.09
    тий
    -0.06
    ете
    -0.06
     عام
    -0.06
    Sources
    -0.06
     Fatal
    -0.06
     Ach
    -0.06
    askets
    -0.06
    LOCK
    -0.06
    آخر
    -0.06
    POSITIVE LOGITS
    钱
    0.08
    <'
    0.07
     serviceName
    0.07
     wine
    0.06
    =""/>↵
    0.06
    笔
    0.06
     coffee
    0.06
     penetrated
    0.06
    рез
    0.06
     logits
    0.06
    Activations Density 0.011%

    No Known Activations