© 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. 58441
    Prev
    Next
    INDEX
    Explanations

    GW

    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
    Relative
    -0.07
     bev
    -0.07
    	idx
    -0.07
    <Message
    -0.07
    еві
    -0.07
    Chuck
    -0.07
    Sigma
    -0.06
    .getDay
    -0.06
     Shades
    -0.06
     Week
    -0.06
    POSITIVE LOGITS
    informatics
    0.07
    SetBranchAddress
    0.06
     erotisk
    0.06
    -bootstrap
    0.06
     queryInterface
    0.06
     состоит
    0.06
    	cl
    0.06
    matchCondition
    0.06
     across
    0.06
    115
    0.06
    Activations Density 0.008%

    No Known Activations