© 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 EvalsExportsinterp-engineNEWAPI 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. 58160
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    The neuron activates on relational prepositions (e.g. “over,” “under,” “based,” “involving”) that introduce context or scope phrases.

    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
    "])){↵
    -0.07
    ")));↵↵
    -0.07
    :");↵↵
    -0.07
    erp
    -0.06
    ึก
    -0.06
    Salt
    -0.06
                                                    ↵
    -0.06
             ↵
    -0.06
    ออกแบบ
    -0.06
    '));↵
    -0.06
    POSITIVE LOGITS
    тов
    0.07
     jon
    0.07
    ANE
    0.07
    цин
    0.06
    ON
    0.06
     Amen
    0.06
     trium
    0.06
     empowering
    0.06
    	typedef
    0.06
     subcontract
    0.06
    Activations Density 0.103%

    No Known Activations