© 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. 73714
    Prev
    Next
    INDEX
    Explanations

    reflect

    np_max-act · gemini-2.0-flash

    This neuron activates on technical mentions of wave reflection (e.g. “reflection,” “reflected,” “reflecting”) in the context of waveguide or guided-wave propagation.

    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
    ysterious
    -0.07
     hybrid
    -0.07
    noon
    -0.06
     серпня
    -0.06
    Biz
    -0.06
    Vs
    -0.06
     світі
    -0.06
    %d
    -0.06
    configured
    -0.06
     HC
    -0.06
    POSITIVE LOGITS
    ]*(
    0.07
     gv
    0.07
     Sinatra
    0.06
    CEF
    0.06
     <>↵
    0.06
     deploying
    0.06
    .imageView
    0.06
    ']));
    0.06
     SMALL
    0.06
     Gi�
    0.06
    Activations Density 0.005%

    No Known Activations