© 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. 44760
    Prev
    Next
    INDEX
    Explanations

    Open

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the substring “Open” in names (e.g. OpenEXR, OpenSIPS, OpenCV), i.e. software or library names beginning with “Open.”

    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
     daleko
    -0.07
     worst
    -0.07
    -Up
    -0.07
    ICODE
    -0.06
     худ
    -0.06
    ippo
    -0.06
     Diet
    -0.06
    analysis
    -0.06
     ціка
    -0.06
     wides
    -0.06
    POSITIVE LOGITS
     Open
    0.09
     стари
    0.07
    .opensource
    0.07
     pressing
    0.06
     mandate
    0.06
     Ethereum
    0.06
    サー
    0.06
     Stamp
    0.06
     Opens
    0.06
    .scope
    0.06
    Activations Density 0.010%

    No Known Activations