© 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. 15-RESID-POST-AA
    6. 109087
    Prev
    Next
    INDEX
    Explanations

    image storage in database

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     často
    -0.07
     이동합니다
    -0.07
    流
    -0.07
    /session
    -0.06
     kill
    -0.06
    .sb
    -0.06
     updateUser
    -0.06
    chemical
    -0.06
    (statement
    -0.06
    包
    -0.06
    POSITIVE LOGITS
     percept
    0.07
     envis
    0.06
     bibli
    0.06
    uib
    0.06
     Stuart
    0.06
    995
    0.06
    ./
    0.06
    іблі
    0.06
     thirty
    0.06
     MOD
    0.06
    Activations Density 0.209%

    No Known Activations