© 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. 88899
    Prev
    Next
    INDEX
    Explanations

    complex

    np_max-act · gemini-2.0-flash

    The neuron responds when the text describes something as a “complex” or “multifaceted” process or procedure.

    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
     registro
    -0.06
     <%=
    -0.06
    HeadersHeight
    -0.06
     Daha
    -0.06
     Vermont
    -0.06
    Attempts
    -0.06
    ethe
    -0.06
    材料
    -0.06
     qc
    -0.06
    Volt
    -0.06
    POSITIVE LOGITS
    øre
    0.07
     ド
    0.06
     nền
    0.06
     Everest
    0.06
     disagreements
    0.06
     battling
    0.06
    :N
    0.06
     lesions
    0.06
     specifics
    0.06
     holdings
    0.06
    Activations Density 0.020%

    No Known Activations