© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 14205
    Prev
    Next
    INDEX
    Explanations

    control

    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
    戸
    -0.06
    Circle
    -0.06
    Ju
    -0.06
    usuario
    -0.06
     pornografia
    -0.06
    Connection
    -0.05
    codigo
    -0.05
    Disk
    -0.05
    	sf
    -0.05
    marked
    -0.05
    POSITIVE LOGITS
    .EventArgs
    0.07
     buy
    0.07
    Submitted
    0.07
     авг
    0.07
    [,
    0.07
     align
    0.07
    ète
    0.07
     sare
    0.07
    .rdf
    0.06
     iCloud
    0.06
    Activations Density 0.028%

    No Known Activations