© 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. 85731
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of numerical measurements (dimensions, lengths, sizes) often given with units (e.g. μm, nm).

    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
    ิโ
    -0.07
     autopsy
    -0.07
     Osw
    -0.07
    hq
    -0.06
    Luke
    -0.06
     оди
    -0.06
     Zeus
    -0.06
    연구
    -0.06
    /misc
    -0.06
     comfy
    -0.06
    POSITIVE LOGITS
     Simone
    0.07
    ****
    0.06
    _sections
    0.06
     accessory
    0.06
    -----------
    0.06
    oodle
    0.06
    él
    0.06
     людей
    0.06
     ACCEPT
    0.06
    具
    0.06
    Activations Density 0.014%

    No Known Activations