© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23-RESID-POST-AA
    11. 101346
    Prev
    Next
    INDEX
    Explanations

    technical, scientific writing

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Twig
    -0.07
     Зав
    -0.06
     kil
    -0.06
     RS
    -0.06
    φυ
    -0.06
     Gret
    -0.06
     conseg
    -0.06
    .StObject
    -0.06
    式会社
    -0.06
     quis
    -0.06
    POSITIVE LOGITS
    (cli
    0.07
     ::=
    0.06
    vtk
    0.06
    ことを
    0.06
     заст
    0.06
    _videos
    0.06
     концентра
    0.06
    .splitContainer
    0.06
     stopwatch
    0.06
     prefixes
    0.06
    Activations Density 0.000%

    No Known Activations