© 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. 5969
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron responds to itinerary-style recommendation phrases, especially the infinitival “to” in “place to …” or “to go …” constructions that suggest destinations or actions.

    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
     =================================================================
    -0.07
    _Service
    -0.07
    061
    -0.07
    ')}↵
    -0.07
    .create
    -0.07
    -treated
    -0.06
     generated
    -0.06
     agrees
    -0.06
     adaptor
    -0.06
     elder
    -0.06
    POSITIVE LOGITS
     DIRECTORY
    0.06
    yclerView
    0.06
     قبل
    0.06
    auge
    0.06
     watt
    0.06
     STEM
    0.06
    ावन
    0.06
     mundo
    0.06
     skulle
    0.06
     nuest
    0.06
    Activations Density 0.030%

    No Known Activations