Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 130327
    Prev
    Next
    INDEX
    Explanations

    ode

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of specific electrode types—most notably the words “anode” and “cathode.”

    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
     Flying
    -0.06
    alerts
    -0.06
     crea
    -0.06
     Having
    -0.06
    _tuple
    -0.06
    ération
    -0.06
    ////////////
    -0.06
     �
    -0.06
     était
    -0.06
    Bins
    -0.06
    POSITIVE LOGITS
    ode
    0.08
     author
    0.07
    :<
    0.07
     duo
    0.07
    ografie
    0.07
    abolic
    0.07
    _cli
    0.07
     paginator
    0.06
    _tid
    0.06
    宜
    0.06
    Activations Density 0.002%

    No Known Activations