© 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. 19-RESID-POST-AA
    11. 124694
    Prev
    Next
    INDEX
    Explanations

    adult

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    炉
    -0.06
     qx
    -0.06
    ->$
    -0.06
    	Assert
    -0.06
    宿
    -0.06
    !!.
    -0.06
    \">\
    -0.05
     Qed
    -0.05
    SEQ
    -0.05
     OWNER
    -0.05
    POSITIVE LOGITS
    	snprintf
    0.07
     해결
    0.07
    607
    0.07
     installed
    0.07
    Both
    0.06
    =========↵
    0.06
    =B
    0.06
     solves
    0.06
     resultant
    0.06
    ��글
    0.06
    Activations Density 0.020%

    No Known Activations