© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13846
    Prev
    Next
    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash

    content related to testing and evaluating semiconductor devices.

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

    The neuron activates on mentions of “test” and its variants (tests, testing, tester, etc.), i.e., references to testing activity.

    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
     zoals
    -0.07
    izace
    -0.07
     Thomas
    -0.06
    _rat
    -0.06
     Geh
    -0.06
    Ware
    -0.06
     Pane
    -0.06
     Rud
    -0.06
    付け
    -0.06
    　j
    -0.06
    POSITIVE LOGITS
     zásob
    0.07
    Britain
    0.07
    (::
    0.06
    icial
    0.06
    學
    0.06
     sympt
    0.06
     weaken
    0.06
     eyebrow
    0.06
    _valor
    0.06
     veřej
    0.06
    Activations Density 0.014%

    No Known Activations