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. 86255
    Prev
    Next
    INDEX
    Explanations

    certainty

    np_max-act · gemini-2.0-flash

    phrases related to government regulations and legislation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron flags phrases that discuss long-term planning or funding certainty (e.g., “long-term,” “certainty,” “plan,” “funding”).

    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
    ्ठ
    -0.07
    Coroutine
    -0.06
    運動
    -0.06
     poo
    -0.06
     jó
    -0.06
     parte
    -0.06
    County
    -0.06
    影響
    -0.06
    ño
    -0.06
    لیم
    -0.06
    POSITIVE LOGITS
    urret
    0.07
    ertainty
    0.07
     uncertainty
    0.06
    ك
    0.06
     finished
    0.06
     QUICK
    0.06
    ится
    0.06
     któ
    0.06
    oolStrip
    0.06
     Register
    0.06
    Activations Density 0.054%

    No Known Activations