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. 26169
    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
     satisfy
    -0.07
    概念
    -0.06
     decency
    -0.06
     ä
    -0.06
    änner
    -0.06
     hät
    -0.06
     videot
    -0.06
     millionaire
    -0.06
     одной
    -0.06
    ντ
    -0.06
    POSITIVE LOGITS
    marker
    0.07
    epy
    0.07
    (food
    0.06
    apter
    0.06
    taskId
    0.06
     ],↵↵
    0.06
    _mB
    0.06
    )||(
    0.06
    (priv
    0.06
     pItem
    0.06
    Activations Density 0.002%

    No Known Activations