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

    Neuronpedia

    APICircuit 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. 84515
    Prev
    Next
    INDEX
    Explanations

    animals

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of laboratory animal subjects (e.g. “animals,” “rats,” “mice,” “hamsters”).

    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
     Entered
    -0.06
     Open
    -0.06
     functional
    -0.06
    fc
    -0.06
    becue
    -0.06
     Cards
    -0.06
     bash
    -0.06
    .logging
    -0.06
    Female
    -0.06
    ()/
    -0.06
    POSITIVE LOGITS
    ційний
    0.07
     itself
    0.07
    '][]
    0.07
     гем
    0.07
     autogenerated
    0.06
     Fam
    0.06
    Yaw
    0.06
     jsonObject
    0.06
     hton
    0.06
    خرید
    0.06
    Activations Density 0.051%

    No Known Activations