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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110696
    Prev
    Next
    INDEX
    Explanations

    coatings

    np_max-act · gemini-2.0-flash

    This neuron activates on chemical product names—especially specific polymer‐based materials and formulations (e.g., resins, adhesives, coatings, sealants).

    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
    orting
    -0.07
    498
    -0.06
    -login
    -0.06
    _require
    -0.06
     averaging
    -0.06
    stantiate
    -0.06
    243
    -0.06
    #↵
    -0.06
     ----------↵
    -0.06
    ABCDEFG
    -0.06
    POSITIVE LOGITS
     самов
    0.07
    nr
    0.07
    ‐
    0.07
    oran
    0.07
     airborne
    0.07
    誰
    0.07
     Constit
    0.06
    Mut
    0.06
    STATIC
    0.06
    ульт
    0.06
    Activations Density 0.014%

    No Known Activations