© 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. 58245
    Prev
    Next
    INDEX
    Explanations

    punctuation, stopwords

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive—it never responds (all its activations are zero).

    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
     unter
    -0.06
    Fac
    -0.06
     bước
    -0.06
    Function
    -0.06
    .heroku
    -0.06
     Sand
    -0.06
     공개
    -0.06
     تهیه
    -0.06
     sich
    -0.06
    بری
    -0.06
    POSITIVE LOGITS
     PropertyInfo
    0.07
     DISP
    0.06
    名稱
    0.06
    _arch
    0.06
     llvm
    0.06
    _emit
    0.06
     TTC
    0.06
     centerY
    0.06
    allback
    0.06
    OMET
    0.06
    Activations Density 0.018%

    No Known Activations