© 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. 38946
    Prev
    Next
    INDEX
    Explanations

    St

    np_max-act · gemini-2.0-flash

    technical terms related to software development and project management.

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

    This neuron responds to the two‐letter token “St,” i.e. words beginning with the letters S-t (as in “Storing,” “Studying,” “Statically,” etc.).

    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
     підвищ
    -0.07
     Республи
    -0.07
     業
    -0.06
    -beta
    -0.06
    gv
    -0.06
    fx
    -0.06
    %↵
    -0.06
    244
    -0.06
     پروژه
    -0.06
    POSITIVE LOGITS
     Tomas
    0.07
    ‌شد
    0.06
     memberships
    0.06
     pomp
    0.06
    	builder
    0.06
     Gott
    0.06
    	DBG
    0.06
    اءة
    0.06
     Spears
    0.06
    JEXEC
    0.06
    Activations Density 0.022%

    No Known Activations