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. 84688
    Prev
    Next
    INDEX
    Explanations

    Catching or collecting

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric values—especially decimals and measurements—in detailed technical or procedural 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
     desp
    -0.06
     gris
    -0.06
    �
    -0.06
     día
    -0.06
     Lamp
    -0.06
    ahi
    -0.06
    token
    -0.06
    Fo
    -0.06
    Later
    -0.06
     Triple
    -0.06
    POSITIVE LOGITS
     discrete
    0.06
     �
    0.06
     عمومی
    0.06
     shemale
    0.06
    	iter
    0.06
    #:
    0.06
    〈
    0.06
    first
    0.06
    Wenn
    0.06
    Base
    0.06
    Activations Density 0.057%

    No Known Activations