© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6429
    Prev
    Next
    INDEX
    Explanations

    union

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting the word “union” (and its variants, e.g. non-union) in the medical‐orthopedic context.

    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
    Marc
    -0.06
    д
    -0.06
     medication
    -0.06
    _NOTIFICATION
    -0.06
    (api
    -0.06
    endDate
    -0.06
     Assessment
    -0.06
    .iso
    -0.06
     contrad
    -0.06
    .pipeline
    -0.06
    POSITIVE LOGITS
     "-//
    0.06
    ooke
    0.06
    ический
    0.06
    下载
    0.06
     цел
    0.06
    quires
    0.06
     traceback
    0.06
    	info
    0.06
     alors
    0.06
    TextWriter
    0.06
    Activations Density 0.004%

    No Known Activations