Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126480
    Prev
    Next
    INDEX
    Explanations

    significance

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “significance,” especially in the phrase “The significance of,” as used in scientific or technical statements.

    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
     obedient
    -0.06
     handsome
    -0.06
    pf
    -0.06
     patents
    -0.06
    Лю
    -0.06
     usual
    -0.06
    yaml
    -0.06
    -platform
    -0.06
    妻
    -0.06
     lavish
    -0.06
    POSITIVE LOGITS
     significance
    0.13
    ificance
    0.09
    ifique
    0.07
     объек
    0.07
     สถาน
    0.07
     signific
    0.07
     ثبت
    0.07
    нач
    0.07
    icolon
    0.07
     velik
    0.07
    Activations Density 0.016%

    No Known Activations