© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91527
    Prev
    Next
    INDEX
    Explanations

    extract

    np_max-act · gemini-2.0-flash

    references to medicinal plants and their therapeutic properties.

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

    The neuron detects mentions of plant or herbal “extract” formulations (e.g., crude, aqueous, hydroalcoholic extracts).

    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
    _survey
    -0.07
    FontSize
    -0.07
     Warner
    -0.07
     Joy
    -0.07
    Queue
    -0.06
    ipc
    -0.06
     tiế
    -0.06
    _pv
    -0.06
     kles
    -0.06
     меч
    -0.06
    POSITIVE LOGITS
    	explicit
    0.07
    Specify
    0.07
    	URL
    0.06
    Exclude
    0.06
    正确
    0.06
    须
    0.06
    мотря
    0.06
     Merch
    0.06
    ','=
    0.06
     squarely
    0.06
    Activations Density 0.006%

    No Known Activations