© 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. 129819
    Prev
    Next
    INDEX
    Explanations

    effect

    np_max-act · gemini-2.0-flash

    This neuron detects tokens from the standard legal‐boilerplate phrase specifying that code provisions are “in effect at all relevant times.”

    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
     ví
    -0.07
     Rd
    -0.06
    :$
    -0.06
     وكانت
    -0.06
     bột
    -0.06
     Reminder
    -0.06
     зали
    -0.06
     excav
    -0.06
    -0.05
     evade
    -0.05
    POSITIVE LOGITS
    ็จ
    0.07
     �
    0.07
    нез
    0.07
     Anything
    0.06
     bás
    0.06
     INITIAL
    0.06
     PARA
    0.06
    \Blueprint
    0.06
     handlers
    0.06
     modest
    0.06
    Activations Density 0.002%

    No Known Activations