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. 130280
    Prev
    Next
    INDEX
    Explanations

    philosophy

    np_max-act · gemini-2.0-flash

    The neuron activates on scholarly/theoretical keywords (e.g. “theorie,” “analyse,” “philosophie,” “explanation”) indicating academic or philosophical discussion.

    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
    由于
    -0.07
     Ты
    -0.06
    numpy
    -0.06
    Cog
    -0.06
     ANSW
    -0.06
    케
    -0.06
    Authority
    -0.06
     uninterrupted
    -0.06
     eve
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Initializing
    0.07
     vazgeç
    0.07
    一个人
    0.07
    _redirect
    0.06
    ;color
    0.06
     своє
    0.06
    _ttl
    0.06
     düş
    0.06
    	stop
    0.06
     yardım
    0.06
    Activations Density 0.010%

    No Known Activations