© 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. 11-RESID-POST-AA
    11. 101117
    Prev
    Next
    INDEX
    Explanations

    Mouse

    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_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
    Negative Logits
    Relation
    -0.08
     rehabilit
    -0.08
     relational
    -0.08
     graf
    -0.08
    trad
    -0.07
    belt
    -0.07
     Ferdinand
    -0.07
     klass
    -0.07
     Wimbledon
    -0.07
    报
    -0.07
    POSITIVE LOGITS
     mouse
    0.11
     mice
    0.10
     Mouse
    0.10
    mouse
    0.08
    once
    0.08
     mur
    0.07
     Mickey
    0.07
     MouseEvent
    0.07
     Murphy
    0.07
    Mouse
    0.07
    Activations Density 0.011%

    No Known Activations