© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 71061
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron detects conversational metadata and speaker/header tokens (system/user/assistant IDs and other special header/formatting markers).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31

    wants and requests

    np_max-act · gpt-5-miniTriggered by @yooniel31
    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
     Castillo
    -0.08
    铁路
    -0.08
     після
    -0.07
     tacos
    -0.07
     여행
    -0.07
     Gardens
    -0.07
    TextBox
    -0.07
    隐
    -0.07
     tranh
    -0.07
     hemp
    -0.07
    POSITIVE LOGITS
    ,''
    0.06
    态
    0.06
     Props
    0.06
    ictionary
    0.06
     getMenuInflater
    0.06
    ufe
    0.06
    {})
    0.06
    ­ing
    0.06
    �
    0.06
    フェ
    0.05
    Activations Density 43.453%

    No Known Activations