© 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. 56081
    Prev
    Next
    INDEX
    Explanations

    provide

    np_max-act · gemini-2.0-flash

    The neuron activates on the verb “provide” (and its present-tense variant “provides”).

    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
     jump
    -0.07
    tick
    -0.07
    итися
    -0.06
     kicking
    -0.06
     screws
    -0.06
     sess
    -0.06
     heads
    -0.06
     buck
    -0.06
     Boss
    -0.06
     bet
    -0.06
    POSITIVE LOGITS
     provide
    0.13
     provides
    0.12
     providing
    0.12
     provided
    0.12
    provided
    0.11
     Providing
    0.10
     PROVIDED
    0.10
    Provid
    0.10
     Provide
    0.09
    Provide
    0.09
    Activations Density 0.145%

    No Known Activations