© 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. 59368
    Prev
    Next
    INDEX
    Explanations

    ">"

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numbers (decimal statistics values) in the document.

    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
    277
    -0.06
     Dt
    -0.06
    bob
    -0.06
    tt
    -0.06
     loro
    -0.06
    020
    -0.06
     yüzde
    -0.06
     canon
    -0.06
    dü
    -0.06
     spy
    -0.06
    POSITIVE LOGITS
    -columns
    0.07
    .pl
    0.07
    _DISCONNECT
    0.07
    .OrdinalIgnoreCase
    0.06
     użytk
    0.06
     invokevirtual
    0.06
    Confirm
    0.06
     помощи
    0.06
    .detectChanges
    0.06
     coordinates
    0.06
    Activations Density 0.000%

    No Known Activations