Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 21076
    Prev
    Next
    INDEX
    Explanations

    suitable

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on instances of the adjective “suitable.”

    oai_token-act-pair · o4-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
    kovou
    -0.07
     recursion
    -0.07
    在线视频
    -0.07
    ;;;;;;
    -0.06
     başında
    -0.06
     limit
    -0.06
    τικές
    -0.06
    .Mobile
    -0.06
    Inputs
    -0.06
    OTA
    -0.06
    POSITIVE LOGITS
    SetTitle
    0.08
    (op
    0.07
    予
    0.07
    628
    0.06
     프로그램
    0.06
     happily
    0.06
     appropriate
    0.06
    SignUp
    0.06
    _ap
    0.06
     esteemed
    0.06
    Activations Density 0.019%

    No Known Activations