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. 84689
    Prev
    Next
    INDEX
    Explanations

    machinery and devices

    np_max-act · gemini-2.0-flash

    The neuron activates on technical mentions of printing equipment—words referring to printers or printing apparatus.

    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
    .with
    -0.09
     sper
    -0.08
     Antonio
    -0.07
    .rating
    -0.07
     guitarist
    -0.07
     Drum
    -0.06
    ờ
    -0.06
    Sw
    -0.06
     wedding
    -0.06
    >().
    -0.06
    POSITIVE LOGITS
    liğine
    0.07
     تط
    0.07
     الأد
    0.06
     espacio
    0.06
     společnosti
    0.06
    -е
    0.06
     blok
    0.06
    BLUE
    0.06
     vector
    0.06
    Khi
    0.06
    Activations Density 0.064%

    No Known Activations