© 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. 55954
    Prev
    Next
    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash

    This neuron detects ASP.NET data‐binding expressions (the “<%# Bind(…) %>” or “<%# Eval(…) %>” markup) in WebForms pages.

    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
     установлен
    -0.08
     Пред
    -0.07
     poner
    -0.07
     CrossAxisAlignment
    -0.07
     STILL
    -0.06
    "All
    -0.06
     хот
    -0.06
    _separator
    -0.06
     Sword
    -0.06
     boton
    -0.06
    POSITIVE LOGITS
    Modify
    0.07
    _PL
    0.06
    .O
    0.06
    allel
    0.06
     Arlington
    0.06
    $IFn
    0.06
    gs
    0.06
    (part
    0.06
    Courier
    0.06
    _Q
    0.06
    Activations Density 0.000%

    No Known Activations