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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 41770
    Prev
    Next
    INDEX
    Explanations

    code/math symbols

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially decimal or fractional number literals—in the 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
    site
    -0.07
    iert
    -0.07
     Wired
    -0.06
    ,u
    -0.06
     querying
    -0.06
     кан
    -0.06
    Php
    -0.06
     fronts
    -0.06
    _Two
    -0.06
    Program
    -0.06
    POSITIVE LOGITS
    -rise
    0.07
    rights
    0.06
     NRA
    0.06
    /ss
    0.06
     영향을
    0.06
     CORPOR
    0.06
     resent
    0.06
     destabil
    0.06
    ;%
    0.06
    	level
    0.06
    Activations Density 0.030%

    No Known Activations