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. 21573
    Prev
    Next
    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash

    technical jargon and programming terms, especially those related to software development and licensing.

    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
    eric
    -0.06
     mod
    -0.06
    ップ
    -0.06
     pivot
    -0.06
     bandwidth
    -0.06
    .ONE
    -0.06
    Unless
    -0.06
    _directory
    -0.06
    (APP
    -0.06
     Since
    -0.06
    POSITIVE LOGITS
    CommandEvent
    0.06
     отдель
    0.06
    :update
    0.06
     وضع
    0.06
    listener
    0.06
    blas
    0.06
    abo
    0.06
    legen
    0.06
     shower
    0.06
    醴醴
    0.06
    Activations Density 0.102%

    No Known Activations