© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128576
    Prev
    Next
    INDEX
    Explanations

    begin

    np_max-act · gemini-2.0-flash

    Delphi code related to creating and displaying user interface elements, specifically forms and images.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects the “BEGIN” (and its variants like “begin”/“END”) keyword that marks the start/end of a PL/SQL or Delphi code block.

    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
    类型
    -0.07
    	mock
    -0.07
     上
    -0.07
    締
    -0.07
     resourceName
    -0.06
     blocker
    -0.06
     Crimson
    -0.06
     disadvantage
    -0.06
     Naomi
    -0.06
    iffe
    -0.06
    POSITIVE LOGITS
    ób
    0.07
    ingular
    0.07
     vagina
    0.06
    يل
    0.06
     prin
    0.06
    \b
    0.06
    [property
    0.06
     lég
    0.06
    >Main
    0.06
    [target
    0.06
    Activations Density 0.001%

    No Known Activations