© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12669
    Prev
    Next
    INDEX
    Explanations

    Breaking records

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of record‐setting or statistical record terms (e.g. “record,” “broke,” “previous record,” “breaking”).

    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
    不要
    -0.06
     wished
    -0.06
     dou
    -0.06
    )();↵
    -0.06
    (cp
    -0.06
    시
    -0.06
     유형
    -0.06
     他
    -0.05
    .join
    -0.05
    (temp
    -0.05
    POSITIVE LOGITS
     banco
    0.07
     Agricult
    0.06
    mino
    0.06
    년에는
    0.06
    едак
    0.06
    Spacing
    0.06
    책
    0.06
     "__
    0.06
     aute
    0.06
    utivo
    0.06
    Activations Density 0.008%

    No Known Activations