© 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. 90704
    Prev
    Next
    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash

    This neuron is sensitive to ordinal references and component numbering (e.g. “first,” “second,” numeric labels) in technical descriptions.

    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
    衣
    -0.07
     hookup
    -0.06
     crossing
    -0.06
     employee
    -0.06
    ть
    -0.06
     tiny
    -0.06
     striker
    -0.06
     people
    -0.06
    _MAXIMUM
    -0.06
     pill
    -0.06
    POSITIVE LOGITS
     daring
    0.07
     respondsToSelector
    0.07
     ellipt
    0.07
     Darren
    0.07
    commend
    0.07
    ốc
    0.07
    (other
    0.07
    	RTLI
    0.06
     vysok
    0.06
    :${
    0.06
    Activations Density 0.018%

    No Known Activations