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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 84451
    Prev
    Next
    INDEX
    Explanations

    therapy

    np_max-act · gemini-2.0-flash

    specific terms and concepts related to gene therapy and genetic disorders.

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

    This neuron detects mentions of medical treatment or therapy terms.

    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
     opendir
    -0.07
     Mitar
    -0.06
    _surf
    -0.06
     novels
    -0.06
     Ov
    -0.06
    .sec
    -0.06
     Sele
    -0.06
     和
    -0.06
    interfaces
    -0.06
    amphetamine
    -0.06
    POSITIVE LOGITS
     cook
    0.07
    -story
    0.06
     asp
    0.06
     column
    0.06
    Dr
    0.06
    OPEN
    0.06
    อดภ
    0.06
     Column
    0.06
     浙江
    0.06
    -parser
    0.06
    Activations Density 0.008%

    No Known Activations