© 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. 110397
    Prev
    Next
    INDEX
    Explanations

    date

    np_max-act · gemini-2.0-flash

    This neuron fires on the token “date” (in any capitalization or context), effectively recognizing date‐related fields or headings.

    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
     suitcase
    -0.07
     createStackNavigator
    -0.07
     jav
    -0.06
     Coin
    -0.06
    _OS
    -0.06
     ocur
    -0.06
     VW
    -0.06
    .states
    -0.06
    Jar
    -0.06
     Rus
    -0.06
    POSITIVE LOGITS
     помощ
    0.07
    contacts
    0.07
    預
    0.06
    _normalize
    0.06
    140
    0.06
    xFC
    0.06
    λέ
    0.06
    opolitan
    0.06
     heightFor
    0.06
    ρχ
    0.06
    Activations Density 0.039%

    No Known Activations