© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30126
    Prev
    Next
    INDEX
    Explanations

    Portuguese football teams

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of football club name abbreviations.

    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
     наз
    -0.07
     David
    -0.06
    localStorage
    -0.06
    ;display
    -0.06
     jets
    -0.06
     bay
    -0.06
    Công
    -0.06
     зроб
    -0.06
    \Desktop
    -0.06
    .*)
    -0.06
    POSITIVE LOGITS
    цин
    0.06
    _PAYMENT
    0.06
    IMIT
    0.06
    _trip
    0.06
    ॉन
    0.06
    ODO
    0.06
    тив
    0.06
    -nil
    0.06
     Il
    0.06
     Khoa
    0.06
    Activations Density 0.008%

    No Known Activations