© 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. 51209
    Prev
    Next
    INDEX
    Explanations

    concert announcements

    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
     truncate
    -0.07
    TOTYPE
    -0.06
     alpha
    -0.06
    はず
    -0.06
     sync
    -0.06
    ner
    -0.06
    ě
    -0.06
    형
    -0.06
     Lumpur
    -0.06
     investors
    -0.06
    POSITIVE LOGITS
    /channel
    0.07
    -cont
    0.07
     kvinn
    0.06
    ousel
    0.06
    (enc
    0.06
    uch
    0.06
    ?("
    0.06
    lerdi
    0.06
     말씀
    0.06
     نگهد
    0.06
    Activations Density 0.015%

    No Known Activations