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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41626
    Prev
    Next
    INDEX
    Explanations

    names of people/places

    np_max-act · gemini-2.0-flash

    This neuron detects fragments of proper names—that is, substrings characteristic of person or place names.

    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
    156
    -0.07
     soda
    -0.07
    argin
    -0.07
    Taken
    -0.06
     Ionic
    -0.06
    velte
    -0.06
    :I
    -0.06
     visionary
    -0.06
    enez
    -0.06
    461
    -0.06
    POSITIVE LOGITS
    _advance
    0.07
    .solution
    0.06
    個人
    0.06
     Мари
    0.06
     zákon
    0.06
     لكل
    0.06
    ("\"
    0.06
    lz
    0.06
    .VarChar
    0.06
    тися
    0.06
    Activations Density 0.088%

    No Known Activations