© 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. 56830
    Prev
    Next
    INDEX
    Explanations

    ray

    np_max-act · gemini-2.0-flash

    This neuron activates on the token “ray” (as in “cathode ray,” “electron beam” contexts), flagging references to electron-beam or CRT-style display technology.

    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
    ambi
    -0.07
     rằng
    -0.06
    ware
    -0.06
    IFO
    -0.06
     Pike
    -0.06
    ôme
    -0.06
     тя
    -0.06
    ुब
    -0.06
    isi
    -0.06
     Unc
    -0.06
    POSITIVE LOGITS
    discard
    0.07
     jScrollPane
    0.07
     squirt
    0.07
    QUENCY
    0.06
     matplotlib
    0.06
     CGContext
    0.06
    Protect
    0.06
     Passing
    0.06
     Points
    0.06
    ÜR
    0.06
    Activations Density 0.000%

    No Known Activations