© 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. 89160
    Prev
    Next
    INDEX
    Explanations

    Database IDs and joining

    np_max-act · gemini-2.0-flash

    This neuron fires on SQL column identifiers (especially foreign‐key style names like `sid`, `cid`, etc.) typically seen in JOIN conditions.

    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
     APP
    -0.08
    Extras
    -0.07
    ("-",
    -0.07
    kc
    -0.07
     PRES
    -0.06
    -br
    -0.06
     soru
    -0.06
    .compress
    -0.06
    .quick
    -0.06
     ترکی
    -0.06
    POSITIVE LOGITS
     Tomáš
    0.07
     Driving
    0.06
    /loader
    0.06
    ceased
    0.06
    γράφ
    0.06
    тий
    0.06
    lesson
    0.06
     dash
    0.06
     işaret
    0.06
    的な
    0.06
    Activations Density 0.010%

    No Known Activations