© 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 EvalsExportsinterp-engineNEWAPI 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. 58396
    Prev
    Next
    INDEX
    Explanations

    strong

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of strong interaction contexts—especially the phrase “strong coupling.”

    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
     yummy
    -0.08
    HTTPHeader
    -0.07
     fourteen
    -0.07
     Mara
    -0.06
     مثال
    -0.06
    "io
    -0.06
     зазнач
    -0.06
    .joda
    -0.06
    (loop
    -0.06
    })"↵
    -0.06
    POSITIVE LOGITS
     treasury
    0.07
     engineers
    0.06
    /db
    0.06
    BoundingClientRect
    0.06
    ocs
    0.06
     dB
    0.06
     Eng
    0.06
     점
    0.06
    bef
    0.06
     abb
    0.06
    Activations Density 0.006%

    No Known Activations