© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73785
    Prev
    Next
    INDEX
    Explanations

    year

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “year” (especially in headings or date-like contexts).

    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
    bung
    -0.07
     funkce
    -0.07
     ambush
    -0.07
    (dst
    -0.07
     dungeon
    -0.07
     doprov
    -0.07
     patch
    -0.06
     moż
    -0.06
    bench
    -0.06
    Magic
    -0.06
    POSITIVE LOGITS
     year
    0.19
     Year
    0.16
     years
    0.16
    Year
    0.15
    year
    0.15
    Years
    0.13
    -year
    0.13
     Years
    0.13
    years
    0.13
     yr
    0.12
    Activations Density 0.095%

    No Known Activations