© 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. 12709
    Prev
    Next
    INDEX
    Explanations

    Copying

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens related to object copying APIs or protocols (e.g. “copy,” “Copying,” “copyWithZone,” “NSCopying”).

    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
    _HEALTH
    -0.07
     mock
    -0.07
    lepší
    -0.07
     valido
    -0.07
    ुग
    -0.07
    อว
    -0.06
    onical
    -0.06
     striker
    -0.06
     svo
    -0.06
    Elapsed
    -0.06
    POSITIVE LOGITS
     QDialog
    0.07
     reminiscent
    0.06
    	enum
    0.06
    始
    0.06
     فبراير
    0.06
     Chairman
    0.06
    nit
    0.06
     инвести
    0.06
    ecd
    0.06
    venient
    0.06
    Activations Density 0.004%

    No Known Activations