© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89130
    Prev
    Next
    INDEX
    Explanations

    CA

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect the “CA” token as it appears in gene names like BRCA1/2.

    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
    -loading
    -0.07
    Stamp
    -0.07
     TT
    -0.07
    }_
    -0.06
    _demo
    -0.06
     Status
    -0.06
     digits
    -0.06
     enemies
    -0.06
    .staff
    -0.06
    {s
    -0.06
    POSITIVE LOGITS
    РА
    0.07
    τογραφ
    0.07
    *dx
    0.06
    SEN
    0.06
     BufferedImage
    0.06
     обычно
    0.06
    циональ
    0.06
     glowing
    0.06
    traditional
    0.06
     Glam
    0.06
    Activations Density 0.001%

    No Known Activations