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

    Neuronpedia

    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. 3-RESID-POST-AA
    11. 121327
    Prev
    Next
    INDEX
    Explanations

    aut

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mats
    -0.06
     novamente
    -0.06
     Bonds
    -0.06
    olu
    -0.06
     Creat
    -0.06
     Marker
    -0.06
     nbytes
    -0.06
    �
    -0.06
    gg
    -0.06
    izar
    -0.06
    POSITIVE LOGITS
    auto
    0.08
     author
    0.07
    ।↵
    0.07
     intros
    0.06
    gesture
    0.06
    _pk
    0.06
    vehicle
    0.06
    	ex
    0.06
    Constraints
    0.06
    axter
    0.06
    Activations Density 0.008%

    No Known Activations