© 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 EvalsExportsinterp-engineNEWAPI 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. 20308
    Prev
    Next
    INDEX
    Explanations

    code

    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
    нка
    -0.06
    -output
    -0.06
    whel
    -0.06
     punish
    -0.06
    fiction
    -0.06
     oci
    -0.06
    	error
    -0.06
    ternet
    -0.06
    ابقات
    -0.05
    /from
    -0.05
    POSITIVE LOGITS
     distributing
    0.07
    -selector
    0.07
    ávis
    0.07
    _GROUP
    0.06
    هد
    0.06
     перер
    0.06
     udál
    0.06
    _gateway
    0.06
     DISTRIBUT
    0.06
    |$
    0.06
    Activations Density 0.082%

    No Known Activations