© 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. 109347
    Prev
    Next
    INDEX
    Explanations

    Add

    np_max-act · gemini-2.0-flash

    This neuron fires on bits of code performing date arithmetic—especially tokens around “Date” methods adding or subtracting days/months (e.g. Date.add, Duration, numeric interval arguments).

    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
    .terminate
    -0.07
     Vancouver
    -0.06
    ेहतर
    -0.06
    :text
    -0.06
    Budget
    -0.06
    :].
    -0.06
     "@
    -0.06
     Across
    -0.06
    شنبه
    -0.06
    /how
    -0.06
    POSITIVE LOGITS
     fitness
    0.07
     brewing
    0.07
    тик
    0.06
    ैज
    0.06
     physicists
    0.06
    actics
    0.06
    озі
    0.06
    PX
    0.06
    (write
    0.06
     cites
    0.06
    Activations Density 0.010%

    No Known Activations