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. 104405
    Prev
    Next
    INDEX
    Explanations

    polar

    np_max-act · gemini-2.0-flash

    terms related to polarization and optical properties of light, especially in the context of optical devices and communication systems.

    oai_token-act-pair · gpt-4o-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
     Cec
    -0.07
     непри
    -0.07
    -point
    -0.07
     impe
    -0.07
     believe
    -0.06
    League
    -0.06
     Vin
    -0.06
     Charlotte
    -0.06
     rain
    -0.06
     HashMap
    -0.06
    POSITIVE LOGITS
    680
    0.06
    231
    0.06
     Trucks
    0.06
    inder
    0.06
    aviors
    0.06
     fertilizer
    0.06
    ผล
    0.06
     UIG
    0.06
    geh
    0.06
     него
    0.06
    Activations Density 0.003%

    No Known Activations