© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 27802
    Prev
    Next
    INDEX
    Explanations

    code/math expressions

    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
    inar
    -0.07
    (strlen
    -0.07
    MN
    -0.07
    網
    -0.06
     Ven
    -0.06
    -mediated
    -0.06
    cxx
    -0.06
    mixed
    -0.06
    =pd
    -0.06
    (client
    -0.06
    POSITIVE LOGITS
     '/',↵
    0.07
     sprav
    0.07
    :'↵
    0.06
     totalement
    0.06
    ümüzde
    0.06
     пока
    0.06
    .isEmpty
    0.06
     případě
    0.06
     getattr
    0.06
     adjective
    0.06
    Activations Density 0.014%

    No Known Activations