© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 88992
    Prev
    Next
    INDEX
    Explanations

    Sorting numbers

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting numeric tokens (numbers, including integers and decimals).

    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
     δ
    -0.06
    ui
    -0.06
    Silver
    -0.06
     PC
    -0.06
    Compose
    -0.06
    Within
    -0.05
    sections
    -0.05
     silver
    -0.05
    (comp
    -0.05
    nte
    -0.05
    POSITIVE LOGITS
     Cups
    0.07
    805
    0.07
     fabrication
    0.07
    _CRC
    0.07
     Specialty
    0.07
     سه
    0.07
     vests
    0.07
    ramids
    0.07
     reservation
    0.07
    �이
    0.07
    Activations Density 0.009%

    No Known Activations