Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1525
    Prev
    Next
    INDEX
    Explanations

    stem

    np_max-act · gemini-2.0-flash

    This neuron identifies mentions of mesenchymal stem cells (or “MSC”/“stem cell” references).

    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
    蕉
    -0.07
    .show
    -0.06
     tobacco
    -0.06
    �
    -0.06
    梨
    -0.06
     deren
    -0.06
    -feedback
    -0.06
     pero
    -0.06
    (cb
    -0.06
    人类
    -0.06
    POSITIVE LOGITS
    papers
    0.07
    atalog
    0.07
    Sleep
    0.06
     pute
    0.06
    	block
    0.06
    atur
    0.06
     organizer
    0.06
    Assertion
    0.06
    که
    0.06
    _front
    0.06
    Activations Density 0.003%

    No Known Activations