© 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. 13444
    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_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
     fixation
    -0.07
     Tỉnh
    -0.06
    år
    -0.06
    	freopen
    -0.06
    mes
    -0.06
     OrderedDict
    -0.06
     greedy
    -0.06
    .embedding
    -0.06
     initWith
    -0.06
    Attention
    -0.06
    POSITIVE LOGITS
    _commands
    0.07
    خواست
    0.06
     graves
    0.06
    _LOCAL
    0.06
     counts
    0.06
     nonetheless
    0.06
     unless
    0.06
     sch
    0.06
    quette
    0.06
     acceso
    0.06
    Activations Density 0.003%

    No Known Activations