© 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. 109501
    Prev
    Next
    INDEX
    Explanations

    package

    np_max-act · gemini-2.0-flash

    packages and definitions related to programming constructs and functionalities.

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

    This neuron detects the occurrence of the keyword “Package” in source‐file documentation comments (e.g. the Go doc header).

    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
     Cowboys
    -0.07
    outlined
    -0.07
    Ash
    -0.07
     Twelve
    -0.07
     hectares
    -0.06
     HttpServlet
    -0.06
    (ft
    -0.06
     Bog
    -0.06
    just
    -0.06
     इक
    -0.06
    POSITIVE LOGITS
     ورود
    0.07
    	super
    0.06
    ลล
    0.06
    orgia
    0.06
    ً،
    0.06
    斗
    0.06
    925
    0.06
    arhus
    0.06
    tection
    0.06
     UD
    0.06
    Activations Density 0.001%

    No Known Activations