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

    Neuronpedia

    Jacobian LensNEW
    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. 38662
    Prev
    Next
    INDEX
    Explanations

    electronics/hardware

    np_max-act · gemini-2.0-flash

    The neuron picks out technical terms indicating measurements, units, model numbers, or battery sizes (e.g. voltages, watts, millimeters, “AA,” “AAA,” 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
     Leone
    -0.07
     adicion
    -0.07
     гид
    -0.07
    艦
    -0.07
     elements
    -0.06
    聚
    -0.06
    -spot
    -0.06
    徽
    -0.06
     devices
    -0.06
     consul
    -0.06
    POSITIVE LOGITS
    ////////////////////////////////////////////////////////////////
    0.07
    (['/
    0.07
     demanded
    0.07
    .'''↵
    0.06
    _formatted
    0.06
    .override
    0.06
    =[[
    0.06
    MORE
    0.06
     taxonomy
    0.06
     Compatible
    0.06
    Activations Density 0.031%

    No Known Activations