© 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. 3-RESID-POST-AA
    6. 121493
    Prev
    Next
    INDEX
    Explanations

    my

    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
    tuk
    -0.06
    greg
    -0.06
    uke
    -0.06
     Teh
    -0.06
    cluded
    -0.06
     automated
    -0.06
     getUsers
    -0.06
     ayr
    -0.06
    sst
    -0.06
     Muse
    -0.06
    POSITIVE LOGITS
     her
    0.07
     Your
    0.07
    raf
    0.07
    Vote
    0.07
     stumble
    0.07
     CPPUNIT
    0.06
     YE
    0.06
    _symbol
    0.06
    abbage
    0.06
     Emblem
    0.06
    Activations Density 0.033%

    No Known Activations