© 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. 15-RESID-POST-AA
    6. 6626
    Prev
    Next
    INDEX
    Explanations

    focus on one thing

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lection
    -0.07
     ترجم
    -0.06
    .server
    -0.06
    dev
    -0.06
     \"$
    -0.06
     हर
    -0.06
     hips
    -0.06
     skoro
    -0.06
    _ACT
    -0.06
    zem
    -0.06
    POSITIVE LOGITS
    Orth
    0.06
    UIAlertView
    0.06
     asbestos
    0.06
     hypoth
    0.06
     CAST
    0.06
    O
    0.06
     Phys
    0.06
     аналог
    0.06
     pourquoi
    0.06
     센
    0.06
    Activations Density 0.033%

    No Known Activations