© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 36431
    Prev
    Next
    INDEX
    Explanations

    Numerical analysis/experiments

    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
     búsqueda
    -0.07
    angement
    -0.06
     suffice
    -0.06
     publication
    -0.06
    atics
    -0.06
    　　 　 　 　 　
    -0.06
    	ff
    -0.06
    恶
    -0.06
    	typ
    -0.06
    .end
    -0.06
    POSITIVE LOGITS
     Sinatra
    0.07
     UITapGestureRecognizer
    0.06
    @foreach
    0.06
    Japanese
    0.06
     Wrestle
    0.06
    Routine
    0.06
     символ
    0.06
     Ford
    0.06
     kvinnor
    0.06
     merg
    0.06
    Activations Density 0.118%

    No Known Activations