© 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. 91358
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    descriptions of chemical companies and their products.

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

    The neuron fires on the “in” of “located in” phrases, i.e. it spots the part of an introduction that states where the company is based.

    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
     Oculus
    -0.06
     sufficiently
    -0.06
    ury
    -0.06
    cmd
    -0.06
     horrors
    -0.06
     zajist
    -0.06
    _attrs
    -0.06
     tờ
    -0.06
     tempor
    -0.06
     Matth
    -0.06
    POSITIVE LOGITS
    .Slf
    0.07
     Rodriguez
    0.07
     Participant
    0.07
    .customer
    0.07
     RouteServiceProvider
    0.07
    ress
    0.06
    Tại
    0.06
     機
    0.06
     Boo
    0.06
    ocup
    0.06
    Activations Density 0.009%

    No Known Activations