© 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. 7070
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence

    np_max-act · gemini-2.0-flash

    The neuron activates on technical machine‐learning terminology (e.g. names of neural-network architectures and algorithm terms).

    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
    gz
    -0.06
    _squared
    -0.06
     Merchant
    -0.06
     Marines
    -0.06
    一点
    -0.06
     ******************************************************************************↵
    -0.06
     monkey
    -0.06
     kitty
    -0.05
     Morg
    -0.05
     fast
    -0.05
    POSITIVE LOGITS
     pasar
    0.08
     Opportunity
    0.07
     컨
    0.07
    ้าม
    0.07
     Cous
    0.07
     Prophet
    0.07
     جم
    0.06
     годы
    0.06
    ��
    0.06
    .I
    0.06
    Activations Density 0.058%

    No Known Activations