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. 11-RESID-POST-AA
    6. 50394
    Prev
    Next
    INDEX
    Explanations

    i

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wx
    -0.07
    Sz
    -0.07
     stm
    -0.06
     organiz
    -0.06
     Liz
    -0.06
     cola
    -0.06
     rag
    -0.06
    stan
    -0.06
     mz
    -0.06
     antennas
    -0.06
    POSITIVE LOGITS
    /e
    0.06
     Fighter
    0.06
    ินทร
    0.06
     còn
    0.06
     即
    0.06
     于
    0.06
    ooke
    0.06
    _SelectedIndexChanged
    0.06
     temperament
    0.06
    .internal
    0.06
    Activations Density 0.013%

    No Known Activations