© 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. 56313
    Prev
    Next
    INDEX
    Explanations

    ray

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of X-ray—particularly the word “X-ray” itself and related instrument names (e.g. ROSAT, PSPC, HRI, Einstein, Chandra, XMM-Newton).

    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
     Pon
    -0.06
     trio
    -0.06
     Thanksgiving
    -0.06
     情
    -0.06
     mor
    -0.06
    麻
    -0.06
     par
    -0.06
     Ά
    -0.06
     glaciers
    -0.06
    Blo
    -0.06
    POSITIVE LOGITS
     disclosing
    0.07
    birthdate
    0.07
    hack
    0.06
    ]',
    0.06
     FactoryGirl
    0.06
    .hits
    0.06
     libertarian
    0.06
    Publish
    0.06
    ไปย
    0.06
     Availability
    0.06
    Activations Density 0.003%

    No Known Activations