© 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. 38786
    Prev
    Next
    INDEX
    Explanations

    operation

    np_max-act · gemini-2.0-flash

    This neuron flags passages introducing or describing the device’s operation, such as “The operation of this … is …” statements.

    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
    enic
    -0.06
     addObserver
    -0.06
     appell
    -0.06
    Unsigned
    -0.06
    ntl
    -0.06
    istence
    -0.06
     글
    -0.06
    вест
    -0.06
    显
    -0.06
     Nobody
    -0.06
    POSITIVE LOGITS
    لمه
    0.07
     případě
    0.07
     route
    0.06
     Math
    0.06
     più
    0.06
    _adv
    0.06
    getPage
    0.06
     Türkçe
    0.06
     держави
    0.06
     anh
    0.06
    Activations Density 0.025%

    No Known Activations