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

    Neuronpedia

    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. 91434
    Prev
    Next
    INDEX
    Explanations

    environment

    np_max-act · gemini-2.0-flash

    The neuron activates on words related to setting up or configuring software environments (e.g. “configurar,” “ambiente,” “execução,” “cluster,” etc.).

    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
    Syn
    -0.07
    Cast
    -0.07
     Resets
    -0.07
    mayın
    -0.07
    ét
    -0.06
     pencils
    -0.06
     plunge
    -0.06
     석
    -0.06
     novels
    -0.06
    694
    -0.06
    POSITIVE LOGITS
    boro
    0.07
     Transparent
    0.06
     Hait
    0.06
    iquid
    0.06
     Dayton
    0.06
     Relief
    0.06
     kicking
    0.06
     frameworks
    0.06
     Habitat
    0.06
     environment
    0.06
    Activations Density 0.019%

    No Known Activations