© 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. 126162
    Prev
    Next
    INDEX
    Explanations

    dates and times

    np_max-act · gemini-2.0-flash

    The neuron predominantly activates on numeric date and time tokens (day numbers, ordinals, months, session numbers), indicating it detects schedule or date references.

    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
     Dillon
    -0.07
     معماری
    -0.07
     Cut
    -0.07
     Donovan
    -0.06
     ΚΑΙ
    -0.06
    .levels
    -0.06
     Duffy
    -0.06
     Mvc
    -0.06
     Judaism
    -0.06
    ук
    -0.06
    POSITIVE LOGITS
    338
    0.08
    َج
    0.07
     질
    0.07
     �
    0.07
     isteyen
    0.06
     usernames
    0.06
    _da
    0.06
    ظˆ
    0.06
     gör
    0.06
     oltre
    0.06
    Activations Density 0.021%

    No Known Activations