© 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. 27-RESID-POST-AA
    11. 10372
    Prev
    Next
    INDEX
    Explanations

    rate, frequency, regularity

    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
    Not in Any Lists

    No Comments

    Negative Logits
     пля
    -0.08
     Food
    -0.07
     minister
    -0.07
     Video
    -0.07
     passion
    -0.06
     Fun
    -0.06
     SECRET
    -0.06
     NOTE
    -0.06
    .Reference
    -0.06
    (step
    -0.06
    POSITIVE LOGITS
     multiplier
    0.07
     já
    0.06
    aux
    0.06
    ull
    0.06
    'on
    0.06
     dismal
    0.06
    ’on
    0.06
    70
    0.06
    _ef
    0.06
    =B
    0.06
    Activations Density 0.039%

    No Known Activations