© 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. 12782
    Prev
    Next
    INDEX
    Explanations

    timezones

    np_max-act · gemini-2.0-flash

    This neuron detects time-related tokens—times and time‐zone abbreviations in event schedules.

    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
    ifix
    -0.07
     هفت
    -0.07
     Geb
    -0.07
    OBJECT
    -0.07
     Amb
    -0.06
     compilers
    -0.06
     scenes
    -0.06
    렀
    -0.06
    україн
    -0.06
    Generally
    -0.06
    POSITIVE LOGITS
     qty
    0.07
     Prep
    0.06
    考え
    0.06
     postage
    0.06
     psychosis
    0.06
    _include
    0.06
    =(-
    0.06
    (.
    0.06
    이라
    0.06
    	strncpy
    0.06
    Activations Density 0.004%

    No Known Activations