© 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. 30204
    Prev
    Next
    INDEX
    Explanations

    due

    np_max-act · gemini-2.0-flash

    chemical compounds used in various industrial applications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on the word “due,” typically marking the causal phrase “due to.”

    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
    Every
    -0.07
    Class
    -0.07
    ák
    -0.07
     Perc
    -0.07
     tossing
    -0.06
    ॉम
    -0.06
     PhpStorm
    -0.06
    簡
    -0.06
     Brass
    -0.06
    .Arrays
    -0.06
    POSITIVE LOGITS
     due
    0.16
     Due
    0.13
    Due
    0.12
    due
    0.12
    ue
    0.09
     according
    0.09
    e
    0.08
    ю
    0.08
    625
    0.08
    ude
    0.08
    Activations Density 0.021%

    No Known Activations