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. 128835
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
     홍
    -0.07
    -',
    -0.07
     meaningful
    -0.06
     목록
    -0.06
     열
    -0.06
     万元
    -0.06
    -в
    -0.06
     nama
    -0.06
    sendKeys
    -0.06
     леч
    -0.06
    POSITIVE LOGITS
    github
    0.07
     collected
    0.07
     Smarty
    0.07
    obec
    0.07
    pet
    0.06
     badges
    0.06
     recursion
    0.06
     tendencies
    0.06
     manners
    0.06
    _interest
    0.06
    Activations Density 0.018%

    No Known Activations