© 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. 125584
    Prev
    Next
    INDEX
    Explanations

    hyphens

    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
     emerg
    -0.07
     mobile
    -0.06
    .Loader
    -0.06
    _INSERT
    -0.06
     Gives
    -0.06
     lofty
    -0.06
     Ultr
    -0.06
     ceremonial
    -0.06
     Inserts
    -0.06
    Retention
    -0.06
    POSITIVE LOGITS
    ORK
    0.07
     点
    0.07
    articles
    0.06
    "(
    0.06
     MASTER
    0.06
     모델
    0.06
     Dual
    0.06
    ────
    0.06
    FFFFFFFF
    0.06
     yandan
    0.06
    Activations Density 0.004%

    No Known Activations