© 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. 9381
    Prev
    Next
    INDEX
    Explanations

    sentence structure

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens—especially year or date mentions—within 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
     Pond
    -0.08
    자가
    -0.06
     incomes
    -0.06
    ]").
    -0.06
    titles
    -0.06
     multicultural
    -0.06
     馬
    -0.06
    οι
    -0.06
     nw
    -0.06
    .rules
    -0.06
    POSITIVE LOGITS
     اتحاد
    0.06
     QAction
    0.06
     स
    0.06
    cisi
    0.06
    ricane
    0.06
     Canadian
    0.06
     которого
    0.06
    (seed
    0.06
     ii
    0.06
     submarine
    0.06
    Activations Density 0.028%

    No Known Activations