© 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. 88920
    Prev
    Next
    INDEX
    Explanations

    Circle drawing code

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals (especially dimensions and coordinates) within SVG/XML attribute values.

    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
    ↵	
↵
    -0.07
    _des
    -0.06
    _SH
    -0.06
    SUM
    -0.06
    _od
    -0.06
    閉
    -0.06
    	Mat
    -0.06
     CES
    -0.06
    sum
    -0.06
     Ter
    -0.06
    POSITIVE LOGITS
     urged
    0.08
     vielleicht
    0.07
     UIWindow
    0.07
    events
    0.06
    ――
    0.06
     dlouh
    0.06
     filmed
    0.06
     story
    0.06
    projection
    0.06
    itional
    0.06
    Activations Density 0.017%

    No Known Activations