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. 22065
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    discussions on scientific processes or methods related to chemical reactions and materials.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     phạm
    -0.07
     deniz
    -0.07
    osals
    -0.07
     Sanayi
    -0.07
     Leer
    -0.06
    oại
    -0.06
    orne
    -0.06
     Hoy
    -0.06
     knit
    -0.06
    -cmpr
    -0.06
    POSITIVE LOGITS
     Coroutine
    0.06
    Anywhere
    0.06
    _RESET
    0.06
    _under
    0.06
     elegant
    0.06
    )*/↵
    0.06
    _dd
    0.06
    ючи
    0.06
    WithDuration
    0.06
    最後
    0.05
    Activations Density 0.005%

    No Known Activations