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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RESID-POST-AA
    6. 93451
    Prev
    Next
    INDEX
    Explanations

    mischief

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     території
    -0.07
    weakSelf
    -0.07
     graduating
    -0.07
     abortions
    -0.07
    .styles
    -0.06
     national
    -0.06
     admire
    -0.06
     substances
    -0.06
    ought
    -0.06
    -over
    -0.06
    POSITIVE LOGITS
     mischief
    0.10
    电子
    0.06
    _CACHE
    0.06
    Settings
    0.06
     pově
    0.06
     postData
    0.06
     créer
    0.06
    zap
    0.06
    节
    0.06
     Pok
    0.06
    Activations Density 0.026%

    No Known Activations