© 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. 8800
    Prev
    Next
    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the adverb “now” (and similar high-impact timing words) that introduce or emphasize a change or new behavior.

    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
    arcer
    -0.06
    ард
    -0.06
    資
    -0.06
     priced
    -0.06
    複
    -0.06
    olv
    -0.06
    aml
    -0.06
     explo
    -0.06
     verdict
    -0.06
    份
    -0.06
    POSITIVE LOGITS
     Чер
    0.08
    	Port
    0.06
     Native
    0.06
     浙江
    0.06
    [cur
    0.06
     Toastr
    0.06
     ΕΛ
    0.06
     Ney
    0.06
     recreation
    0.06
    	LP
    0.06
    Activations Density 0.029%

    No Known Activations