© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29554
    Prev
    Next
    INDEX
    Explanations

    Electrical voltage

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of variable symbols (like “V” with subscripts or “omega.p”) and their numeric values—that is, tokens representing measured physical quantities.

    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
    リア
    -0.06
     월
    -0.06
    ียรต
    -0.06
    hotel
    -0.06
    erk
    -0.06
    ้ไข
    -0.06
    
    -0.06
     orgy
    -0.06
    ظيف
    -0.06
    124
    -0.06
    POSITIVE LOGITS
    john
    0.06
    "]))
    0.06
     वह
    0.06
    /control
    0.06
    \Twig
    0.06
    ATTRIBUTE
    0.06
     Session
    0.06
    ButtonClick
    0.06
     kardeş
    0.06
    *****↵
    0.06
    Activations Density 0.053%

    No Known Activations