© 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. 59228
    Prev
    Next
    INDEX
    Explanations

    sub

    np_max-act · gemini-2.0-flash

    This neuron activates on terms indicating mathematical sub-structures (e.g. “subfield,” “subalgebra,” etc.).

    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
     目
    -0.07
     understood
    -0.06
    	RTE
    -0.06
    ountains
    -0.06
    ّت
    -0.06
     WEIGHT
    -0.06
    ΑΡ
    -0.06
    уса
    -0.06
     hài
    -0.06
    -all
    -0.06
    POSITIVE LOGITS
     admirable
    0.07
    _Core
    0.07
     Hind
    0.07
     Sob
    0.06
     Gover
    0.06
    ).</
    0.06
     jailed
    0.06
     arasındaki
    0.06
    .drop
    0.06
     WIDTH
    0.06
    Activations Density 0.006%

    No Known Activations