© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59436
    Prev
    Next
    INDEX
    Explanations

    image

    np_max-act · gemini-2.0-flash

    The neuron is strongly triggered by the word “image” (especially when it appears as part of technical terms like “image pickup” or “image reading”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     bottles
    -0.07
    	R
    -0.07
     Lights
    -0.07
     rejected
    -0.07
    _refptr
    -0.07
    (cnt
    -0.06
    stras
    -0.06
    DRAW
    -0.06
     Melissa
    -0.06
    	Output
    -0.06
    POSITIVE LOGITS
     SCE
    0.06
     PSP
    0.06
     Độ
    0.06
    (error
    0.06
     doporuč
    0.06
     rog
    0.06
     iş
    0.06
     professionally
    0.06
     gid
    0.06
    /report
    0.06
    Activations Density 0.006%

    No Known Activations