© 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. 7-RESID-POST-AA
    6. 54599
    Prev
    Next
    INDEX
    Explanations

    ##

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agos
    -0.06
    avatar
    -0.06
    467
    -0.06
    AYER
    -0.06
    -day
    -0.06
    additional
    -0.06
    �
    -0.06
    chor
    -0.06
    ?,
    -0.06
    _FOR
    -0.06
    POSITIVE LOGITS
     اله
    0.07
    .setBounds
    0.07
    による
    0.06
    <Entry
    0.06
    Complex
    0.06
     errores
    0.06
    Distinct
    0.06
    mongodb
    0.06
     Scheduled
    0.06
     muy
    0.06
    Activations Density 0.022%

    No Known Activations