© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68564
    Prev
    Next
    INDEX
    Explanations

    24

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric volume or issue numbers in academic citations (the small integers appearing before the colon in journal references).

    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
     grouping
    -0.07
     stint
    -0.07
    _fa
    -0.07
     Lam
    -0.07
    steady
    -0.07
    تى
    -0.07
    ata
    -0.07
     deaths
    -0.07
    assigned
    -0.07
    ětš
    -0.07
    POSITIVE LOGITS
    24
    0.13
    25
    0.09
    ۲۴
    0.08
    v
    0.08
    240
    0.08
     Ver
    0.08
    23
    0.07
    024
    0.07
     Vác
    0.07
     ㅇ
    0.07
    Activations Density 0.047%

    No Known Activations