© 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. 101351
    Prev
    Next
    INDEX
    Explanations

    establishments and industries

    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
     Garten
    -0.06
     mirror
    -0.06
     circular
    -0.06
     güven
    -0.06
     Fare
    -0.06
    fight
    -0.06
    fields
    -0.06
    potential
    -0.06
     prospective
    -0.06
     cultural
    -0.06
    POSITIVE LOGITS
    ισε
    0.07
     мот
    0.07
    GIT
    0.06
    _trace
    0.06
     �
    0.06
    _tracks
    0.06
     locate
    0.06
    oh
    0.06
     footsteps
    0.06
     falta
    0.06
    Activations Density 0.102%

    No Known Activations