© 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. 92080
    Prev
    Next
    INDEX
    Explanations

    Intel

    np_max-act · gemini-2.0-flash

    programming keywords and structure related to software licensing.

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

    The neuron activates on occurrences of the token “Intel,” marking instances of the company name in code comments and headers.

    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
     burst
    -0.07
    いう
    -0.06
     southwestern
    -0.06
    gateway
    -0.06
     LO
    -0.06
    EEE
    -0.06
    _classes
    -0.06
    ssel
    -0.06
     CSL
    -0.06
    달
    -0.06
    POSITIVE LOGITS
    mites
    0.07
     Slider
    0.07
     inequality
    0.06
     Episcopal
    0.06
     insulation
    0.06
     dispos
    0.06
     नगर
    0.06
     mia
    0.06
    Esta
    0.06
     asynchronously
    0.06
    Activations Density 0.006%

    No Known Activations