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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84599
    Prev
    Next
    INDEX
    Explanations

    teaching and learning

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases that emphasize the learner’s active, hands-on participation or engagement in the learning process.

    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
     Twist
    -0.07
     procur
    -0.06
    (delay
    -0.06
     Handler
    -0.06
    .defaults
    -0.06
     Thrones
    -0.06
    Modules
    -0.06
    การท
    -0.06
    >ID
    -0.06
    Elapsed
    -0.06
    POSITIVE LOGITS
    oose
    0.07
    oslav
    0.06
     zvyš
    0.06
     말씀
    0.06
    раз
    0.06
    巴
    0.06
     moder
    0.06
     commonplace
    0.06
     přisp
    0.06
     kari
    0.06
    Activations Density 0.057%

    No Known Activations