Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 125356
    Prev
    Next
    INDEX
    Explanations

    network

    np_max-act · gemini-2.0-flash

    This neuron detects account‐verification or “welcome back to our VIP network/site” login and activation notices.

    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
    _wrap
    -0.07
    	M
    -0.06
     loop
    -0.06
     Republican
    -0.06
    _DEFINE
    -0.06
    افع
    -0.06
     BO
    -0.06
    _CENTER
    -0.06
     subs
    -0.06
     Beş
    -0.06
    POSITIVE LOGITS
    ляются
    0.08
    ंघ
    0.07
    етель
    0.06
     arranged
    0.06
     adalah
    0.06
     Autos
    0.06
    sts
    0.06
     semester
    0.06
     seasoning
    0.06
    اسية
    0.06
    Activations Density 0.006%

    No Known Activations