© 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. 105829
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron fires on phrasing of a user’s request, especially “I want to …​” style constructions indicating an action the user intends.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    JavaScript-related code snippets and operations.

    oai_token-act-pair · gpt-4o-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
    edl
    -0.08
     honored
    -0.07
    _BY
    -0.07
     元
    -0.07
    ۴۰
    -0.07
    Transactional
    -0.06
    Extend
    -0.06
    enan
    -0.06
    .Remove
    -0.06
    ियन
    -0.06
    POSITIVE LOGITS
    Coffee
    0.07
     membres
    0.06
     Kız
    0.06
     vict
    0.06
     طبی
    0.06
    �
    0.06
    ATTERN
    0.06
    　　　　 　
    0.06
    _HELP
    0.06
     Cay
    0.06
    Activations Density 0.093%

    No Known Activations