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. 86104
    Prev
    Next
    INDEX
    Explanations

    Industries and associations

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the forest‐products industry—words like forest, wood, products, pulp, paper, sector, association, 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
     nets
    -0.07
    atrix
    -0.07
     Parents
    -0.07
    todo
    -0.06
     Однако
    -0.06
     indicate
    -0.06
     contexts
    -0.06
    udents
    -0.06
    asant
    -0.06
     Pan
    -0.06
    POSITIVE LOGITS
    /sdk
    0.07
     вим
    0.06
     paramString
    0.06
    CAF
    0.06
     označ
    0.06
    手机
    0.06
     националь
    0.06
     aVar
    0.06
     учас
    0.06
    	UN
    0.06
    Activations Density 0.029%

    No Known Activations