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. 19-RESID-POST-AA
    6. 44925
    Prev
    Next
    INDEX
    Explanations

    is

    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
    工具
    -0.07
    SQ
    -0.07
    .download
    -0.06
     smoked
    -0.06
    .delay
    -0.06
     �
    -0.06
     auc
    -0.06
     Verde
    -0.06
    ute
    -0.06
     cơ
    -0.06
    POSITIVE LOGITS
     fandom
    0.06
    icrosoft
    0.06
    distinct
    0.06
     astounding
    0.06
    Anderson
    0.06
     recognised
    0.06
     Kontakt
    0.06
     linux
    0.06
     ====
    0.06
     sito
    0.06
    Activations Density 0.039%

    No Known Activations