© 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. 27-RESID-POST-AA
    11. 101129
    Prev
    Next
    INDEX
    Explanations

    device

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	stats
    -0.07
     payroll
    -0.07
     run
    -0.06
     aston
    -0.06
     slope
    -0.06
     Montgomery
    -0.06
     autumn
    -0.06
     palms
    -0.06
     Autumn
    -0.06
     tempted
    -0.06
    POSITIVE LOGITS
    Device
    0.10
     device
    0.09
    device
    0.09
     Device
    0.09
    .rec
    0.08
    aceutical
    0.08
    dev
    0.08
    vak
    0.08
    ане
    0.08
    .userAgent
    0.07
    Activations Density 0.040%

    No Known Activations