© 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. 55448
    Prev
    Next
    INDEX
    Explanations

    solutions

    np_max-act · gemini-2.0-flash

    The neuron fires on technical phrases announcing classes of exact solutions—especially “solutions,” “multi-center,” “supergravity,” and related descriptors—in high-level theoretical physics contexts.

    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
    ाल
    -0.06
    Jones
    -0.06
    ショ
    -0.06
    	text
    -0.06
    ，但
    -0.06
     önc
    -0.06
    elt
    -0.06
     gays
    -0.06
     плеч
    -0.06
    Participant
    -0.06
    POSITIVE LOGITS
     destino
    0.07
    ่าย
    0.06
    _PARSER
    0.06
     ΕΛ
    0.06
     Diet
    0.06
     Erie
    0.06
     elektronik
    0.06
     autob
    0.06
     qualche
    0.06
     sei
    0.06
    Activations Density 0.010%

    No Known Activations