Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99874
    Prev
    Next
    INDEX
    Explanations

    )

    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
    _refptr
    -0.08
    .fastjson
    -0.06
     encontr
    -0.06
     چه
    -0.06
     paní
    -0.06
    owo
    -0.06
     Torrent
    -0.05
    ToInt
    -0.05
    -qu
    -0.05
     synonymous
    -0.05
    POSITIVE LOGITS
    Structure
    0.08
    раста
    0.06
    GIT
    0.06
    бина
    0.06
     Produkt
    0.06
    addWidget
    0.06
    主义
    0.06
     тогда
    0.06
    <input
    0.06
    उत
    0.06
    Activations Density 0.005%

    No Known Activations