© 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. 91543
    Prev
    Next
    INDEX
    Explanations

    cricket test matches

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of international cricket matches—especially “Test” matches and other International (e.g. Twenty20) fixtures.

    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
     Cod
    -0.07
     مک
    -0.07
    _ENTRY
    -0.06
    (Level
    -0.06
    uple
    -0.06
     Catal
    -0.06
     Milky
    -0.06
     Grove
    -0.06
     Sleep
    -0.06
    arp
    -0.06
    POSITIVE LOGITS
    /tests
    0.07
    no
    0.06
    normally
    0.06
    �
    0.06
    iliği
    0.06
    .Bit
    0.06
     čist
    0.06
    тех
    0.06
     √
    0.06
    asiswa
    0.06
    Activations Density 0.002%

    No Known Activations