© 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. 23301
    Prev
    Next
    INDEX
    Explanations

    proposed

    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
    =params
    -0.06
    _fun
    -0.06
     bisc
    -0.06
    ญ
    -0.06
    INVAL
    -0.06
    Base
    -0.06
     Stern
    -0.06
    拟
    -0.06
     vide
    -0.06
    oste
    -0.06
    POSITIVE LOGITS
    quiz
    0.07
     Options
    0.06
    ++++++++
    0.06
     mmap
    0.06
     epid
    0.06
     bulunmaktadır
    0.06
    inverse
    0.06
     Influ
    0.06
     arsch
    0.06
    Advertisements
    0.06
    Activations Density 0.008%

    No Known Activations