© 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. 56691
    Prev
    Next
    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash

    This neuron spots numeric attribute values (especially decimal numbers) in XML/IB document tags.

    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
     harms
    -0.06
    iliar
    -0.06
    щество
    -0.06
    etě
    -0.06
    ubat
    -0.06
    пор
    -0.06
    집
    -0.06
     fault
    -0.06
     devel
    -0.06
    Dev
    -0.06
    POSITIVE LOGITS
     رسانه
    0.07
    .ensure
    0.07
    .UNKNOWN
    0.07
     наличи
    0.07
     PRIMARY
    0.07
     getType
    0.07
    (?:
    0.07
     pursuant
    0.07
     merupakan
    0.06
    507
    0.06
    Activations Density 0.003%

    No Known Activations