© 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. 89893
    Prev
    Next
    INDEX
    Explanations

    Spirituality

    np_max-act · gemini-2.0-flash

    The neuron responds to content words in the body of the assistant’s long multi‐sentence responses, effectively marking tokens that belong to the assistant’s main reply text.

    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
    される
    -0.07
    ↵            
    ↵
    -0.06
    िव
    -0.06
     발생
    -0.06
    熟
    -0.06
    회
    -0.06
     catastrophic
    -0.06
    _creator
    -0.06
    抑
    -0.06
     doporuč
    -0.06
    POSITIVE LOGITS
    Minute
    0.07
    lift
    0.06
    _online
    0.06
     sprayed
    0.06
    -str
    0.06
     hát
    0.06
    scroll
    0.06
    orph
    0.06
     الحل
    0.06
    bgcolor
    0.06
    Activations Density 0.008%

    No Known Activations