© 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. 91589
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    license-related terms and phrases.

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

    The neuron detects the phrase used in license headers referring to reproducing the disclaimer “in the documentation and/or other materials provided with the distribution.”

    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
     weekends
    -0.07
    -------↵↵
    -0.06
     Titans
    -0.06
     Elk
    -0.06
    λό
    -0.06
     execution
    -0.06
    arters
    -0.06
     Lun
    -0.06
     maneuver
    -0.06
     scenarios
    -0.06
    POSITIVE LOGITS
     طبقه
    0.07
     کردم
    0.06
    UAGE
    0.06
     dealloc
    0.06
    lín
    0.06
     collaborated
    0.06
     Brill
    0.06
     HomeComponent
    0.06
    =[];↵
    0.06
     доктор
    0.06
    Activations Density 0.002%

    No Known Activations