© 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. 123605
    Prev
    Next
    INDEX
    Explanations

    :

    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
    Negative Logits
    -0.06
     ola
    -0.06
    dados
    -0.06
    _trampoline
    -0.06
    @d
    -0.05
    ůr
    -0.05
     tuổi
    -0.05
     glossy
    -0.05
    -vesm
    -0.05
     odp
    -0.05
    POSITIVE LOGITS
    şı
    0.07
    luğu
    0.07
     harvested
    0.07
     sacrificed
    0.07
    .Ct
    0.06
    composer
    0.06
    _EFFECT
    0.06
     ning
    0.06
    حة
    0.06
     Course
    0.06
    Activations Density 0.023%

    No Known Activations