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. 84391
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron detects numeric location references, such as street‐block or address numbers in news text.

    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
    ansom
    -0.07
     Yen
    -0.07
     Dashboard
    -0.07
     ensl
    -0.07
    _heap
    -0.06
    amps
    -0.06
     Polymer
    -0.06
    outs
    -0.06
    append
    -0.06
    ages
    -0.06
    POSITIVE LOGITS
     Animated
    0.06
     Copyright
    0.06
     creator
    0.06
     série
    0.06
     preview
    0.06
     undergraduate
    0.06
     tablespoons
    0.06
    _quant
    0.06
     hailed
    0.06
    /_
    0.06
    Activations Density 0.003%

    No Known Activations