© 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. 126562
    Prev
    Next
    INDEX
    Explanations

    enh

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “contrast-enhanced” (and related “enhanced”) imaging descriptions.

    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
     contain
    -0.08
    macros
    -0.07
    trait
    -0.06
    алеж
    -0.06
    ibrate
    -0.06
    _b
    -0.06
     plays
    -0.06
    ematics
    -0.06
    appear
    -0.06
     laying
    -0.06
    POSITIVE LOGITS
    NSURLSession
    0.07
     использов
    0.07
     Ive
    0.07
     круп
    0.07
    	NullCheck
    0.07
     और
    0.07
     advertisement
    0.06
    ="#
    0.06
     |--
    0.06
     Additionally
    0.06
    Activations Density 0.002%

    No Known Activations