© 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. 54221
    Prev
    Next
    INDEX
    Explanations

    section

    np_max-act · gemini-2.0-flash

    medical terminology related to aortic dissection and its treatment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron selectively activates on the term “dissection” (and its morphological variants like “dissect,” “dissecting”) in medical contexts.

    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
    _many
    -0.07
     slun
    -0.07
     contraception
    -0.06
    CHANNEL
    -0.06
    管
    -0.06
    Quant
    -0.06
    ęki
    -0.06
     mek
    -0.06
    STAT
    -0.06
    Clusters
    -0.06
    POSITIVE LOGITS
     enlisted
    0.07
    .last
    0.07
     Artikel
    0.06
    Latch
    0.06
     Combat
    0.06
     confidential
    0.06
    敗
    0.06
     Honestly
    0.06
     miserable
    0.06
     Granted
    0.06
    Activations Density 0.001%

    No Known Activations