© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 9037
    Prev
    Next
    INDEX
    Explanations

    showed, revealed

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of medical imaging procedures and their findings (e.g. CT, MRI, imaging results).

    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
    !),
    -0.07
    ething
    -0.07
    DAT
    -0.06
    Ek
    -0.06
     skateboard
    -0.06
    -Clause
    -0.06
     impoverished
    -0.06
    _DEPTH
    -0.06
    。</
    -0.06
    !»
    -0.06
    POSITIVE LOGITS
     optimum
    0.07
    agic
    0.07
     고려
    0.07
    =\"
    0.06
    active
    0.06
     findOne
    0.06
    OLID
    0.06
     negot
    0.06
     نقد
    0.06
     accomplishments
    0.06
    Activations Density 0.011%

    No Known Activations