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. 19-RESID-POST-AA
    6. 83500
    Prev
    Next
    INDEX
    Explanations

    Video game categories

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Drug
    -0.07
    _current
    -0.07
    ktop
    -0.07
    rise
    -0.07
    _MIDDLE
    -0.06
    131
    -0.06
    Caption
    -0.06
    EFAULT
    -0.06
     controversial
    -0.06
    الإ
    -0.06
    POSITIVE LOGITS
     شف
    0.07
     bekom
    0.07
    ificação
    0.06
    {
    0.06
     refusing
    0.06
     beide
    0.06
    -Mail
    0.06
     Royals
    0.06
    就算
    0.06
    inheritDoc
    0.06
    Activations Density 0.005%

    No Known Activations