© 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. 15-RESID-POST-AA
    11. 37683
    Prev
    Next
    INDEX
    Explanations

    under

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relocation
    -0.07
     relocate
    -0.06
     nga
    -0.06
     fasta
    -0.06
    loha
    -0.06
     boj
    -0.06
     piracy
    -0.06
     qi
    -0.06
    poons
    -0.06
    :length
    -0.06
    POSITIVE LOGITS
     Under
    0.15
     under
    0.14
    Under
    0.13
     UNDER
    0.12
    under
    0.11
    -under
    0.10
    _under
    0.09
     underneath
    0.09
     onder
    0.09
     underst
    0.09
    Activations Density 0.050%

    No Known Activations