© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89853
    Prev
    Next
    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric date and time markers (e.g. day numbers, years, and month names), effectively finding tokens that denote dates or chronological 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
    ени
    -0.08
    ация
    -0.07
     sophomore
    -0.07
     maker
    -0.07
    	address
    -0.06
     unordered
    -0.06
    termination
    -0.06
    flation
    -0.06
     suggestions
    -0.06
    ,key
    -0.06
    POSITIVE LOGITS
    _WIFI
    0.07
    =='
    0.07
    dispose
    0.07
     şart
    0.07
    referer
    0.06
    SQLException
    0.06
    ıyla
    0.06
     mischief
    0.06
     금액
    0.06
    Include
    0.06
    Activations Density 0.013%

    No Known Activations