© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 127043
    Prev
    Next
    INDEX
    Explanations

    possible

    np_max-act · gemini-2.0-flash

    technical terminology related to mechanical or electronic devices, particularly in the context of engineering and manufacturing.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the formal, patent-style language that introduces possible embodiments or capabilities—i.e. the “it is possible/for example”-type statements in the invention description.

    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
     Крім
    -0.06
    стру
    -0.06
    wu
    -0.06
     YEARS
    -0.06
    戻
    -0.06
    ibold
    -0.06
     gere
    -0.06
    ографія
    -0.06
     Hope
    -0.06
     Loop
    -0.06
    POSITIVE LOGITS
     홍
    0.08
     Reduction
    0.07
    เคร
    0.06
     krb
    0.06
    تس
    0.06
     graphite
    0.06
     Gri
    0.06
    )↵↵↵↵
    0.06
     milli
    0.06
    #g
    0.06
    Activations Density 0.033%

    No Known Activations