© 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
    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. 43073
    Prev
    Next
    INDEX
    Explanations

    material

    np_max-act · gemini-2.0-flash

    The neuron activates on the phrase “material fact,” i.e. it’s detecting mentions of materiality in legal representations.

    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
    icolon
    -0.07
     narrow
    -0.07
     deputy
    -0.07
     ils
    -0.06
     вересня
    -0.06
    ’on
    -0.06
    ());
↵
↵
    -0.06
     promoted
    -0.06
    .ContextCompat
    -0.06
    Expand
    -0.06
    POSITIVE LOGITS
     봐
    0.06
     ціка
    0.06
     susceptible
    0.06
    dB
    0.06
     Caf
    0.06
    terraform
    0.06
     Wheat
    0.06
     мал
    0.06
    RITE
    0.06
     meas
    0.06
    Activations Density 0.002%

    No Known Activations