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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 41992
    Prev
    Next
    INDEX
    Explanations

    defined

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially decimal numbers and section or citation references.

    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
    _proc
    -0.07
    flatten
    -0.07
    Battery
    -0.07
     rode
    -0.06
    -dist
    -0.06
     Ethics
    -0.06
    	root
    -0.06
    สม
    -0.06
     drinks
    -0.06
     form
    -0.06
    POSITIVE LOGITS
     सब
    0.06
     presented
    0.06
    -ended
    0.06
     Austrian
    0.06
    的な
    0.06
     모델
    0.06
    orsch
    0.06
    inel
    0.05
    prene
    0.05
     Lockheed
    0.05
    Activations Density 0.009%

    No Known Activations