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

    Neuronpedia

    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. 6173
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric immediates—especially constants used as displacement or offset values in assembly memory operands.

    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
     SplashScreen
    -0.07
     Tour
    -0.06
     unpopular
    -0.06
    GMT
    -0.06
     meters
    -0.06
    /her
    -0.06
    Tour
    -0.06
     crib
    -0.06
     خوان
    -0.06
     spot
    -0.06
    POSITIVE LOGITS
    在地
    0.08
    法
    0.07
    .vertex
    0.07
     المج
    0.07
     artic
    0.07
    ава
    0.07
    "time
    0.06
    ewise
    0.06
    "]))↵
    0.06
     запах
    0.06
    Activations Density 0.002%

    No Known Activations