Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91550
    Prev
    Next
    INDEX
    Explanations

    trip

    np_max-act · gemini-2.0-flash

    This neuron activates on travel-planning language, especially words like “trip,” “travel,” “visiting,” and related itinerary terms.

    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
     approves
    -0.07
     Root
    -0.07
     TH
    -0.07
    ıkl
    -0.07
    -linked
    -0.07
     Bristol
    -0.06
     Theatre
    -0.06
     STD
    -0.06
    imag
    -0.06
     UNITY
    -0.06
    POSITIVE LOGITS
     maur
    0.07
    นวย
    0.06
     getPage
    0.06
     ребенка
    0.06
    Mitch
    0.06
    getStatus
    0.06
    (['/
    0.06
     accompl
    0.06
    _information
    0.06
    青
    0.05
    Activations Density 0.031%

    No Known Activations