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. 130669
    Prev
    Next
    INDEX
    Explanations

    hypnosis and sleep

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of sleep disorders (e.g. insomnia) and related pharmacological treatments (e.g. hypnotics, sleep drugs).

    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
    mx
    -0.07
    Lady
    -0.07
     Spiel
    -0.06
     mc
    -0.06
     Strong
    -0.06
     reels
    -0.06
    şiv
    -0.06
      
    -0.06
    /*↵
    -0.06
     mn
    -0.06
    POSITIVE LOGITS
    criptive
    0.06
    ومات
    0.06
     करक
    0.06
     ödül
    0.06
     acclaim
    0.06
    گذ
    0.06
    кам
    0.06
     Hobby
    0.06
    .$.
    0.06
    ocular
    0.06
    Activations Density 0.003%

    No Known Activations