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. 130236
    Prev
    Next
    INDEX
    Explanations

    ina

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of DNA sequencing technologies and associated instrument or library‐preparation kit names.

    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
    諸
    -0.07
    876
    -0.07
     uğ
    -0.07
     Richie
    -0.07
    Chain
    -0.06
     Queens
    -0.06
     انگ
    -0.06
    -core
    -0.06
    Billy
    -0.06
    HF
    -0.06
    POSITIVE LOGITS
    	pthread
    0.07
    CATEGORY
    0.07
    <GameObject
    0.06
     documenting
    0.06
    rita
    0.06
    接着
    0.06
    北京
    0.06
    pty
    0.06
     amazon
    0.06
    nici
    0.06
    Activations Density 0.003%

    No Known Activations