© 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. 11-RESID-POST-AA
    11. 76891
    Prev
    Next
    INDEX
    Explanations

    Code asking for names

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     نقشه
    -0.06
     квад
    -0.06
    _spec
    -0.06
    통
    -0.06
     teenagers
    -0.06
    ervlet
    -0.06
    케
    -0.06
    Ymd
    -0.06
    離
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Castle
    0.06
    Ι
    0.06
     Sak
    0.06
     interes
    0.06
    audit
    0.06
     인기
    0.06
    .fake
    0.06
     impressed
    0.06
    .CV
    0.06
    Meal
    0.06
    Activations Density 0.019%

    No Known Activations