© 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. 44551
    Prev
    Next
    INDEX
    Explanations

    Rwanda

    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
    fieldName
    -0.07
     Đề
    -0.07
     capitals
    -0.07
    (IO
    -0.07
     merge
    -0.07
    colour
    -0.06
    Severity
    -0.06
     horizon
    -0.06
     chambre
    -0.06
    φέρει
    -0.06
    POSITIVE LOGITS
     Rwanda
    0.13
     Rw
    0.09
     tvar
    0.07
     nuest
    0.06
     removeObject
    0.06
    !!!!
    0.06
    rowData
    0.06
     dwar
    0.06
    Tests
    0.06
    ("`
    0.06
    Activations Density 0.001%

    No Known Activations