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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57705
    Prev
    Next
    INDEX
    Explanations

    op

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens (step numbers and decimal values) in procedural instructions.

    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
    .target
    -0.07
    \Page
    -0.07
     vision
    -0.07
    iert
    -0.06
    Recognition
    -0.06
    �
    -0.06
     Также
    -0.06
    ARI
    -0.06
    Vari
    -0.06
     Hai
    -0.06
    POSITIVE LOGITS
     receivers
    0.07
     ту
    0.06
    |#
    0.06
    derived
    0.06
    /&
    0.06
     капит
    0.06
     sympath
    0.06
     artillery
    0.06
     См
    0.06
     hospitalized
    0.06
    Activations Density 0.463%

    No Known Activations