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. 8551
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron activates on ordinal date markers, specifically numbers followed by "th" (e.g., "26 th", "17 th", "20 th", etc.).

    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
    lt
    -0.08
    hp
    -0.08
    Maint
    -0.07
    .mb
    -0.07
     hp
    -0.06
    Prepare
    -0.06
    Chelsea
    -0.06
    ولا
    -0.06
     ignorant
    -0.06
    Yahoo
    -0.06
    POSITIVE LOGITS
     días
    0.06
     �
    0.06
     blackColor
    0.06
     мав
    0.06
     myfile
    0.06
    	ORDER
    0.06
     MARK
    0.06
     Hash
    0.06
    	Assert
    0.06
     різ
    0.06
    Activations Density 0.004%

    No Known Activations