© 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. 90886
    Prev
    Next
    INDEX
    Explanations

    medical study

    np_max-act · gemini-2.0-flash

    This neuron picks out the names of the clinical intervention or treatment being tested (e.g. hypothermia, laser therapy, intervention group labels, drug names, etc.).

    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
    akk
    -0.07
     symb
    -0.06
    егист
    -0.06
    周收录
    -0.06
    론
    -0.06
    _fig
    -0.06
     farther
    -0.06
    $k
    -0.06
    'ex
    -0.06
    "H
    -0.06
    POSITIVE LOGITS
    Emer
    0.07
     maxLength
    0.07
     preocup
    0.07
     technological
    0.07
     Hizmetleri
    0.06
    approval
    0.06
     ;↵↵↵
    0.06
    \HttpFoundation
    0.06
     стала
    0.06
    -performance
    0.06
    Activations Density 0.031%

    No Known Activations