© 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
    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. 126609
    Prev
    Next
    INDEX
    Explanations

    request

    np_max-act · gemini-2.0-flash

    The neuron fires on code tokens that make HTTP requests (e.g. “make”, “requests”, “GET/POST”, “HTTP”), so it’s detecting when the text is describing or showing an HTTP API call.

    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
     zer
    -0.06
     CACHE
    -0.06
     landfill
    -0.06
     FIR
    -0.06
    ो,
    -0.06
    %-
    -0.06
    Một
    -0.06
    .ErrorCode
    -0.06
    .fetchall
    -0.06
    covery
    -0.06
    POSITIVE LOGITS
     Shim
    0.07
     QString
    0.06
     ist
    0.06
    ocyte
    0.06
    Sea
    0.06
     det
    0.06
     drž
    0.06
     alg
    0.06
    	no
    0.06
     TextInput
    0.06
    Activations Density 0.035%

    No Known Activations