© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30082
    Prev
    Next
    INDEX
    Explanations

    nuts

    np_max-act · gemini-2.0-flash

    This neuron is sensitive to specialized scientific or technical jargon (including precise measurements, complex domain-specific terms, and multi-syllabic technical vocabulary).

    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
     Haz
    -0.07
     dado
    -0.07
     晴
    -0.06
     Sample
    -0.06
     latch
    -0.06
    infinity
    -0.06
    شنامه
    -0.06
    ุบ
    -0.06
    _occ
    -0.06
     Intelligent
    -0.06
    POSITIVE LOGITS
     Brewer
    0.06
    atég
    0.06
    inciple
    0.06
     versus
    0.06
     firsthand
    0.06
    .MAIN
    0.06
          ↵↵
    0.06
     operational
    0.06
    Rib
    0.06
    нова
    0.06
    Activations Density 0.467%

    No Known Activations