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. 83504
    Prev
    Next
    INDEX
    Explanations

    personal narratives

    np_max-act · gemini-2.0-flash

    first-person statements

    np_max-act · gemini-2.5-flashTriggered by @aardvarkkr
    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
    •my list
    wholesomeness

    No Comments

    Negative Logits
    legation
    -0.07
     Tub
    -0.07
     Carter
    -0.06
     SCORE
    -0.06
    variant
    -0.06
     Authorized
    -0.06
     Ep
    -0.06
     Interview
    -0.06
    �
    -0.06
     Roses
    -0.06
    POSITIVE LOGITS
     je
    0.07
    良い
    0.06
     partie
    0.06
    ":@"
    0.06
     mare
    0.06
    ****************
    0.06
    lä
    0.06
     migli
    0.06
     слаб
    0.06
    diği
    0.06
    Activations Density 0.204%

    No Known Activations