© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56831
    Prev
    Next
    INDEX
    Explanations

    Western

    np_max-act · gemini-2.0-flash

    the roles of specific proteins and signaling pathways in cancer progression and cellular response mechanisms.

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

    The neuron detects mentions of “Western blot” used to report protein expression assays.

    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
    Rod
    -0.06
    �
    -0.06
     quat
    -0.06
    _sta
    -0.06
    _Do
    -0.06
     Ideally
    -0.06
     Math
    -0.06
    Param
    -0.06
    step
    -0.06
     prod
    -0.06
    POSITIVE LOGITS
     $_
    0.07
    )v
    0.06
    уществ
    0.06
    cies
    0.06
    icaid
    0.06
     provisions
    0.06
    村
    0.06
    expert
    0.06
     woven
    0.06
     toArray
    0.06
    Activations Density 0.002%

    No Known Activations