© 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. 11-RESID-POST-AA
    11. 46819
    Prev
    Next
    INDEX
    Explanations

    fashion and clothing

    np_max-act · gemini-2.0-flash

    product descriptions related to fashion items.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wrapping
    -0.07
    ysics
    -0.07
     underscore
    -0.07
    math
    -0.07
    	stack
    -0.07
     spherical
    -0.06
     paradise
    -0.06
     client
    -0.06
     mathematics
    -0.06
     formally
    -0.06
    POSITIVE LOGITS
     پا
    0.06
    ोज
    0.06
     interp
    0.06
    029
    0.06
    міністра
    0.06
     Contributors
    0.06
    *>::
    0.06
     Комп
    0.06
     banyak
    0.06
    +"
    0.05
    Activations Density 0.022%

    No Known Activations