© 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. 7-RESID-POST-AA
    11. 36105
    Prev
    Next
    INDEX
    Explanations

    tennis

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.06
     resisted
    -0.06
     reveal
    -0.06
     weg
    -0.06
     duplicates
    -0.06
     WHICH
    -0.06
     YOU
    -0.05
     distur
    -0.05
     "(\<
    -0.05
    	seq
    -0.05
    POSITIVE LOGITS
     Promo
    0.07
    .core
    0.06
     �
    0.06
     органів
    0.06
     Coy
    0.06
     القرآن
    0.06
    έν
    0.06
    -num
    0.06
    \Module
    0.06
    يان
    0.06
    Activations Density 0.712%

    No Known Activations