© 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. 41399
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron detects clauses that specify payment dates adjusted to business days, especially the phrase “on the immediately preceding Business Day.”

    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
    mongoose
    -0.06
    (sent
    -0.06
     Injector
    -0.06
     ergonomic
    -0.06
    repr
    -0.06
    _deriv
    -0.06
    edef
    -0.06
     vals
    -0.06
    Uint
    -0.06
     notebook
    -0.06
    POSITIVE LOGITS
     trim
    0.06
     �
    0.06
    โป
    0.06
     WON
    0.06
    setMessage
    0.06
     tělo
    0.06
     alleen
    0.06
      
    0.06
    /************************************************
    0.06
     обще
    0.05
    Activations Density 0.011%

    No Known Activations