© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92379
    Prev
    Next
    INDEX
    Explanations

    Months

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of month abbreviations (e.g., “Jan,” “Feb,” “Mar,” etc.) in patent citation dates.

    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
     Peach
    -0.07
     Bütün
    -0.07
     रहन
    -0.07
    _filter
    -0.06
    Pod
    -0.06
     Consumption
    -0.06
     Seasons
    -0.06
    анный
    -0.06
    AKE
    -0.06
     Ved
    -0.06
    POSITIVE LOGITS
    pname
    0.08
    يا
    0.06
    lify
    0.06
    Ath
    0.06
    .DateField
    0.06
     assoc
    0.06
    navigationBar
    0.06
    dbg
    0.06
     capitalize
    0.06
     apar
    0.06
    Activations Density 0.004%

    No Known Activations