© 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. 58848
    Prev
    Next
    INDEX
    Explanations

    clearing things up

    np_max-act · gemini-2.0-flash

    This neuron activates on words and phrases that express clarifying or “clearing up” confusion.

    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
     save
    -0.07
    PRINT
    -0.07
    ersion
    -0.07
     struk
    -0.06
    Primitive
    -0.06
    _READ
    -0.06
    Suite
    -0.06
    pointer
    -0.06
     Boulevard
    -0.06
     Cameras
    -0.06
    POSITIVE LOGITS
    ursos
    0.06
    ?),
    0.06
    ़े
    0.06
     třídy
    0.06
    opo
    0.06
     Pascal
    0.06
    ismus
    0.06
    องท
    0.06
    方向
    0.06
    _met
    0.06
    Activations Density 0.022%

    No Known Activations