© 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. 3-RESID-POST-AA
    11. 95538
    Prev
    Next
    INDEX
    Explanations

    the

    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
     vente
    -0.07
     قول
    -0.06
    izons
    -0.06
     spies
    -0.06
    (){}↵
    -0.06
     bö
    -0.06
     checkout
    -0.06
    Amb
    -0.06
            ↵        ↵
    -0.06
    スペ
    -0.06
    POSITIVE LOGITS
    .getClassName
    0.06
    voir
    0.06
    (default
    0.06
     Cursor
    0.06
     crochet
    0.06
    καν
    0.06
    ,alpha
    0.06
    يت
    0.06
    (IOException
    0.06
    ẳn
    0.06
    Activations Density 0.151%

    No Known Activations