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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 43531
    Prev
    Next
    INDEX
    Explanations

    Belittling/demeaning

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases used to demean, objectify, or degrade people or groups.

    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
     travels
    -0.08
    _example
    -0.07
     ghost
    -0.06
     HttpStatusCodeResult
    -0.06
     risky
    -0.06
     epoll
    -0.06
     letter
    -0.06
     replication
    -0.06
    幾
    -0.06
    chi
    -0.06
    POSITIVE LOGITS
     affair
    0.07
    sında
    0.07
     elevate
    0.07
     Sanct
    0.06
    ific
    0.06
    prav
    0.06
     Validates
    0.06
    loan
    0.06
    fragment
    0.06
     Antoine
    0.06
    Activations Density 0.016%

    No Known Activations