© 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. 19-RESID-POST-AA
    11. 114840
    Prev
    Next
    INDEX
    Explanations

    computer programming code

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StringTokenizer
    -0.07
     notation
    -0.06
    nx
    -0.06
    เง
    -0.06
    \Session
    -0.06
     Mesh
    -0.06
    .userName
    -0.06
     ramifications
    -0.06
    Visible
    -0.06
    Label
    -0.06
    POSITIVE LOGITS
     resend
    0.07
     scenic
    0.06
    爸
    0.06
    舰
    0.06
    농
    0.06
     حسين
    0.06
     postseason
    0.06
     towards
    0.06
    _hresult
    0.06
     Chand
    0.06
    Activations Density 0.011%

    No Known Activations