© 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. 55563
    Prev
    Next
    INDEX
    Explanations

    Dates and times

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of R’s date‐time classes and data.table functions (e.g. “POSIXct,” “data.table,” “round_date”).

    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
    URATION
    -0.07
      
    -0.07
    емо
    -0.07
     рекоменду
    -0.07
       
    -0.07
    атів
    -0.06
    できます
    -0.06
     hook
    -0.06
     ValidationError
    -0.06
    .clip
    -0.06
    POSITIVE LOGITS
     mortgages
    0.07
    женер
    0.06
    @Configuration
    0.06
     HtmlWebpackPlugin
    0.06
     stew
    0.06
    gesture
    0.06
     '%'
    0.06
     rounding
    0.06
    灰
    0.06
    ASM
    0.06
    Activations Density 0.011%

    No Known Activations