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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 91520
    Prev
    Next
    INDEX
    Explanations

    Insurance

    np_max-act · gemini-2.0-flash

    The neuron consistently detects occurrences of the word “insurance” (in any context).

    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
     Walk
    -0.07
    Path
    -0.07
     ADHD
    -0.07
     point
    -0.07
     Dost
    -0.07
    彦
    -0.07
     Path
    -0.07
    (team
    -0.07
     Mitarbeiter
    -0.07
    leaflet
    -0.07
    POSITIVE LOGITS
     Insurance
    0.13
     insurance
    0.11
    Insurance
    0.10
    UN
    0.08
     postage
    0.07
    ison
    0.07
    )
    0.07
    ongan
    0.07
     страх
    0.07
     Ins
    0.07
    Activations Density 0.009%

    No Known Activations