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. 84444
    Prev
    Next
    INDEX
    Explanations

    Muslim

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “Muslim.”

    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
    _VERIFY
    -0.06
    leftright
    -0.06
    239
    -0.06
     Εξ
    -0.06
    :"#
    -0.06
     aunque
    -0.06
     plt
    -0.06
     Everett
    -0.06
    _format
    -0.06
    016
    -0.06
    POSITIVE LOGITS
     Muslim
    0.11
     muslim
    0.11
    Muslim
    0.10
     mysl
    0.08
     Muslims
    0.08
    -Muslim
    0.08
     Mbps
    0.07
     datasource
    0.07
     Mueller
    0.07
    (always
    0.07
    Activations Density 0.004%

    No Known Activations