© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7488
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects the closing brace token (“}”) that ends a code block.

    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
    omite
    -0.06
     Looking
    -0.06
     dieses
    -0.06
    cept
    -0.06
    ection
    -0.06
    functional
    -0.06
     Seeing
    -0.06
     Stewart
    -0.06
    spin
    -0.06
    Increasing
    -0.06
    POSITIVE LOGITS
    ToOne
    0.07
    .jd
    0.06
    .pm
    0.06
     읽
    0.06
     тяжел
    0.06
    ProcessEvent
    0.06
    atorial
    0.06
     asla
    0.06
    .s
    0.06
    щими
    0.06
    Activations Density 0.061%

    No Known Activations