© 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. 45308
    Prev
    Next
    INDEX
    Explanations

    UV

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of ultraviolet/sun exposure—i.e. tokens referring to “UV,” “ultraviolet,” “sun,” and related radiation terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    information related to the effects of ultraviolet (UV) radiation on skin health and cancer risk.

    oai_token-act-pair · gpt-4o-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
     sple
    -0.08
    Partner
    -0.06
    .Sprite
    -0.06
    олит
    -0.06
    Av
    -0.06
    _wo
    -0.06
    увати
    -0.06
    Io
    -0.06
    ullet
    -0.06
     silicon
    -0.06
    POSITIVE LOGITS
     cherche
    0.07
     publi
    0.07
     altın
    0.07
    hours
    0.06
     avez
    0.06
     PropertyValue
    0.06
     май
    0.06
    .PREFERRED
    0.06
     Jugend
    0.06
     vowed
    0.06
    Activations Density 0.004%

    No Known Activations