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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 38865
    Prev
    Next
    INDEX
    Explanations

    code variables

    np_max-act · gemini-2.0-flash

    This neuron activates on Python code tokens related to making HTTP requests and checking responses (e.g. requests.get, response.status_code == 200).

    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
     plaats
    -0.07
    Tester
    -0.06
     pursued
    -0.06
     ihm
    -0.06
    цент
    -0.06
     receives
    -0.06
    (content
    -0.06
    Bay
    -0.06
    .RES
    -0.06
    Terminal
    -0.06
    POSITIVE LOGITS
     coronavirus
    0.07
     BoxFit
    0.07
     angled
    0.07
    .getInteger
    0.07
     notas
    0.06
     enterprise
    0.06
     hopeful
    0.06
     Synd
    0.06
     DataColumn
    0.06
     şik
    0.06
    Activations Density 0.010%

    No Known Activations