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. 109583
    Prev
    Next
    INDEX
    Explanations

    review

    np_max-act · gemini-2.0-flash

    This neuron detects in-text literature citations, particularly phrases pointing to reviews (e.g. “for review, see …”).

    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
     Y
    -0.07
    یه
    -0.07
     شرق
    -0.06
     up
    -0.06
     Queue
    -0.06
    .Util
    -0.06
    IN
    -0.06
     Share
    -0.06
     pepper
    -0.06
     م
    -0.06
    POSITIVE LOGITS
    Install
    0.07
    lify
    0.07
    []>(
    0.06
    有什么
    0.06
     필요
    0.06
    	cf
    0.06
    ốn
    0.06
     &'
    0.06
    刺
    0.06
    encv
    0.06
    Activations Density 0.011%

    No Known Activations