© 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. 30069
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    The neuron primarily flags SQL keywords (e.g. SELECT, AS, GROUP BY) in the text.

    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
    -ad
    -0.07
    ワ
    -0.07
     rollout
    -0.06
     assisted
    -0.06
     annunci
    -0.06
    患
    -0.06
     ad
    -0.06
     갑
    -0.06
     classifications
    -0.06
    (File
    -0.06
    POSITIVE LOGITS
     THAN
    0.07
    veal
    0.07
    QRSTUVWXYZ
    0.07
    alytics
    0.06
    toDouble
    0.06
    .PI
    0.06
    CppI
    0.06
    名前
    0.06
    pagen
    0.06
     Desk
    0.06
    Activations Density 0.002%

    No Known Activations