© 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. 79291
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     cyclists
    -0.07
     rivers
    -0.06
    unity
    -0.06
    lying
    -0.06
    innacle
    -0.06
    UNITY
    -0.06
    Warnings
    -0.06
    ただ
    -0.06
    вещ
    -0.06
    ating
    -0.06
    POSITIVE LOGITS
     sklad
    0.06
     раздел
    0.06
    $email
    0.06
    	es
    0.06
     पस
    0.06
     말했다
    0.06
     ''↵↵
    0.06
    ')])↵
    0.06
     Ağustos
    0.06
     dealer
    0.06
    Activations Density 0.026%

    No Known Activations