© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 91171
    Prev
    Next
    INDEX
    Explanations

    ammon

    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
     доз
    -0.07
     hintText
    -0.07
    qw
    -0.07
     traveler
    -0.07
    .calendar
    -0.06
     traditions
    -0.06
     년도별
    -0.06
     anth
    -0.06
    adb
    -0.06
     moderne
    -0.06
    POSITIVE LOGITS
    Impro
    0.07
    ettel
    0.06
    キュ
    0.06
    Va
    0.06
    ,被
    0.06
     crappy
    0.06
     Corona
    0.06
    errs
    0.06
    !'
    0.06
    From
    0.06
    Activations Density 0.003%

    No Known Activations