© 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. 9510
    Prev
    Next
    INDEX
    Explanations

    pet

    np_max-act · gemini-2.0-flash

    The neuron detects the phrase “pet. denied” (i.e. citations noting that a petition was denied) in legal-document footers.

    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
     Fluid
    -0.06
     thinker
    -0.06
    _UN
    -0.06
     Tire
    -0.06
    adden
    -0.06
     cert
    -0.05
     agar
    -0.05
    REAK
    -0.05
     Magnet
    -0.05
     iki
    -0.05
    POSITIVE LOGITS
    щё
    0.07
    好的
    0.07
    ;i
    0.07
     функ
    0.07
     occupancy
    0.06
    Shutdown
    0.06
    )b
    0.06
    งเป
    0.06
    دیگر
    0.06
    owania
    0.06
    Activations Density 0.001%

    No Known Activations