© 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. 27-RESID-POST-AA
    11. 35668
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Website
    -0.06
     언어
    -0.06
    inal
    -0.06
     makeover
    -0.06
    据
    -0.06
    Forg
    -0.06
     Extension
    -0.06
     transcripts
    -0.06
     feat
    -0.06
     LocalDateTime
    -0.06
    POSITIVE LOGITS
     açık
    0.07
     abs
    0.07
     multiplying
    0.07
     모르
    0.07
     Rahul
    0.07
    _gas
    0.06
     проп
    0.06
     obec
    0.06
    .]
    0.06
     unsubscribe
    0.06
    Activations Density 0.003%

    No Known Activations