© 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. 38555
    Prev
    Next
    INDEX
    Explanations

    units

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the phrase “units of measure” (including code identifiers like UnitsOfMeasure) in the text.

    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
    /do
    -0.06
     cohesion
    -0.06
    _COL
    -0.06
    誤
    -0.06
    (path
    -0.06
     Another
    -0.06
    .deep
    -0.06
    ography
    -0.06
    /edit
    -0.06
    -do
    -0.06
    POSITIVE LOGITS
    s
    0.11
    lıklar
    0.10
     Adams
    0.10
    mes
    0.10
    ns
    0.09
    vers
    0.09
     Hayes
    0.08
    iams
    0.08
     Williams
    0.08
    mons
    0.08
    Activations Density 0.645%

    No Known Activations