© 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. 3-RESID-POST-AA
    11. 123733
    Prev
    Next
    INDEX
    Explanations

    to

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chamber
    -0.07
    ricane
    -0.06
    Expense
    -0.06
    าษ
    -0.06
    ri
    -0.06
     rate
    -0.06
    azines
    -0.06
    .GridView
    -0.06
     describe
    -0.06
     обст
    -0.06
    POSITIVE LOGITS
     spol
    0.07
     stimuli
    0.06
     slov
    0.06
     davranış
    0.06
     unaware
    0.06
    Kill
    0.06
    ETO
    0.06
     ве
    0.06
     unmistak
    0.06
     право
    0.06
    Activations Density 0.069%

    No Known Activations