© 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. 56334
    Prev
    Next
    INDEX
    Explanations

    AI and computer systems

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on tokens referring to the language model itself (e.g. “machine,” “model,” “LM/LLM,” “training,” etc.), i.e. when the text is talking about the AI/ML model.

    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
    Aug
    -0.07
    igt
    -0.07
    인데
    -0.07
    716
    -0.07
     Aug
    -0.06
    됩니다
    -0.06
    andi
    -0.06
    Ion
    -0.06
     ска
    -0.06
    ultip
    -0.06
    POSITIVE LOGITS
     gover
    0.07
     coder
    0.06
    عم
    0.06
     comeback
    0.06
    .viewer
    0.06
    .hasClass
    0.06
     polyline
    0.06
    .Selected
    0.06
     Opcode
    0.06
     título
    0.06
    Activations Density 0.050%

    No Known Activations