© 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. 551
    Prev
    Next
    INDEX
    Explanations

    Lasers

    np_max-act · gemini-2.0-flash

    The neuron fires on technical numerical specifications—especially laser parameters such as wavelengths, power or energy values, and related unit tokens.

    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
     diaper
    -0.07
     těchto
    -0.07
     З
    -0.06
    士
    -0.06
     Бог
    -0.06
     own
    -0.06
     Bro
    -0.06
    PLAN
    -0.06
    ух
    -0.06
     パ
    -0.06
    POSITIVE LOGITS
    AssignableFrom
    0.06
    =out
    0.06
     requestData
    0.06
     WHERE
    0.06
    istency
    0.06
    essed
    0.06
    (@"
    0.06
     "~
    0.06
    ={[↵
    0.06
     divisions
    0.06
    Activations Density 0.009%

    No Known Activations