© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29735
    Prev
    Next
    INDEX
    Explanations

    packing

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of packed‐bed or fixed‐film filter media (packing, beds, biofilters, films) in descriptions of engineered columns or reactor apparatus.

    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
     докум
    -0.08
     прит
    -0.06
     sher
    -0.06
    <Path
    -0.06
    (surface
    -0.06
     flap
    -0.06
     fences
    -0.06
     fend
    -0.06
    .byte
    -0.06
    .dim
    -0.05
    POSITIVE LOGITS
    implemented
    0.07
    -package
    0.06
     Whatsapp
    0.06
    ์น
    0.06
    醴
    0.06
    츠
    0.06
    같은
    0.06
     無
    0.06
    ##
    0.06
     undocumented
    0.06
    Activations Density 0.007%

    No Known Activations