© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 19-RESID-POST-AA
    11. 86461
    Prev
    Next
    INDEX
    Explanations

    for

    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
     modeled
    -0.07
     blockers
    -0.07
     lineWidth
    -0.07
    .fx
    -0.07
    TimeZone
    -0.07
     захист
    -0.07
     Ahmed
    -0.07
     힘
    -0.07
     DefaultValue
    -0.07
     zřejmě
    -0.07
    POSITIVE LOGITS
               ↵
    0.07
    ottom
    0.06
     خورد
    0.06
    Chelsea
    0.06
     hete
    0.06
    .choice
    0.05
    -j
    0.05
    tog
    0.05
     بالإ
    0.05
    ngen
    0.05
    Activations Density 0.165%

    No Known Activations