© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125269
    Prev
    Next
    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash

    mentions of technical hard skills and tool/library names in resumes and job descriptions.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    ósito
    -0.08
    ANDROID
    -0.07
    =".
    -0.06
     ویژگی
    -0.06
    .getEntity
    -0.06
     सरक
    -0.06
    OU
    -0.06
     PHY
    -0.06
    \Admin
    -0.06
     cinco
    -0.06
    POSITIVE LOGITS
     çoğ
    0.07
     ш
    0.06
    _ang
    0.06
    ヤ
    0.06
    фік
    0.06
    InterfaceOrientation
    0.06
    AutoresizingMaskIntoConstraints
    0.06
    ‑
    0.06
     �
    0.06
    IndexPath
    0.06
    Activations Density 16.920%

    No Known Activations