© 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. 11-RESID-POST-AA
    6. 74908
    Prev
    Next
    INDEX
    Explanations

    completion

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bà
    -0.07
     बत
    -0.06
     scared
    -0.06
    Ant
    -0.06
     devices
    -0.06
     Medicine
    -0.06
    á
    -0.06
     sanctioned
    -0.06
     Desired
    -0.06
     HOLDERS
    -0.06
    POSITIVE LOGITS
     glitch
    0.07
    ميم
    0.07
    trainer
    0.07
    .low
    0.07
    <div
    0.06
    办理
    0.06
     hepsi
    0.06
    perfil
    0.06
     المل
    0.06
    ,id
    0.06
    Activations Density 0.000%

    No Known Activations