© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6263
    Prev
    Next
    INDEX
    Explanations

    colon, quotation marks

    np_max-act · gemini-2.0-flash

    The neuron fires on the JSON field names used for finalized meeting schedules (the keys specifying date, week, month, time, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    conversations related to scheduling and meeting arrangements.

    oai_token-act-pair · gpt-4o-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
    -u
    -0.07
     addAction
    -0.07
     ambigu
    -0.06
    џџџџџџџџ
    -0.06
    ofil
    -0.06
    /';↵↵
    -0.06
    .Stage
    -0.06
    енью
    -0.06
    uggage
    -0.06
    ouis
    -0.06
    POSITIVE LOGITS
     caratter
    0.06
    CN
    0.06
    .inflate
    0.06
     dug
    0.06
     disap
    0.06
     arose
    0.06
     largo
    0.06
     restarting
    0.06
     getConfig
    0.06
    /export
    0.06
    Activations Density 0.059%

    No Known Activations