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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 77225
    Prev
    Next
    INDEX
    Explanations

    region

    np_max-act · gemini-2.0-flash

    The neuron fires on passages that define or locate a geographic region—i.e. text describing an area or region and where it lies.

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

    geographical regions involved in conflicts.

    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
    @admin
    -0.07
     půj
    -0.07
     رم
    -0.07
     حل
    -0.06
     سرو
    -0.06
    Pointer
    -0.06
     tarn
    -0.06
     parseFloat
    -0.06
     perpetr
    -0.06
     Immediate
    -0.06
    POSITIVE LOGITS
     sensed
    0.07
    roupe
    0.07
     requester
    0.07
    TEAM
    0.07
     organic
    0.07
     IR
    0.06
    }-{
    0.06
     Meng
    0.06
    ђ
    0.06
    tid
    0.06
    Activations Density 0.023%

    No Known Activations