© 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. 9080
    Prev
    Next
    INDEX
    Explanations

    code errors

    np_max-act · gemini-2.0-flash

    The neuron fires on words and symbols that describe code example outcomes (compilation results, errors, successes, failures).

    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
     Commod
    -0.07
     carpets
    -0.06
     bean
    -0.06
    -make
    -0.06
    仔
    -0.06
    .Directory
    -0.06
     Powder
    -0.06
    dw
    -0.06
    Secretary
    -0.06
    ycop
    -0.06
    POSITIVE LOGITS
     अख
    0.07
    (sq
    0.06
    ’une
    0.06
     prenatal
    0.06
     Logistic
    0.06
     روح
    0.06
    ’.
    0.06
    的情况
    0.06
    ,’
    0.06
    sym
    0.06
    Activations Density 0.034%

    No Known Activations