© 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. 15-RESID-POST-AA
    11. 20394
    Prev
    Next
    INDEX
    Explanations

    iterate

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     REQ
    -0.07
    	boost
    -0.07
     defenses
    -0.07
    Allocator
    -0.07
     bak
    -0.06
    ificates
    -0.06
     checkbox
    -0.06
     build
    -0.06
     Jac
    -0.06
    ज
    -0.06
    POSITIVE LOGITS
    UNIT
    0.07
    States
    0.07
    Aggregate
    0.06
    ?><?
    0.06
    classNames
    0.06
    _Per
    0.06
     logging
    0.06
    MG
    0.06
     Â
    0.06
    _Abstract
    0.06
    Activations Density 0.017%

    No Known Activations