© 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. 68418
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of numeric quantifiers (cardinal numbers and measurements) in descriptive 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
     Kant
    -0.07
    _cross
    -0.06
     belang
    -0.06
     Bitcoins
    -0.06
    vd
    -0.06
     البر
    -0.06
     theat
    -0.06
     helps
    -0.06
     představ
    -0.06
    在地
    -0.06
    POSITIVE LOGITS
     kardeş
    0.06
    -Owned
    0.06
    _margin
    0.06
     payout
    0.06
     �
    0.06
     sø
    0.06
    ΗΝ
    0.06
    údo
    0.06
     lãnh
    0.06
    ış
    0.06
    Activations Density 0.024%

    No Known Activations