© 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. 54363
    Prev
    Next
    INDEX
    Explanations

    consequential

    np_max-act · gemini-2.0-flash

    The neuron activates on the term “consequential” (as in “consequential damages”) in license or disclaimer boilerplate.

    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
     trapping
    -0.07
     studio
    -0.06
     proxies
    -0.06
     feed
    -0.06
     Minority
    -0.06
    \Field
    -0.06
     Infrastructure
    -0.06
     Monitor
    -0.06
    -market
    -0.06
    	sp
    -0.06
    POSITIVE LOGITS
    PushButton
    0.08
    _GT
    0.07
     Cena
    0.06
    śli
    0.06
    asmine
    0.06
     Amar
    0.06
     حص
    0.06
    μι
    0.06
     Haskell
    0.06
     biri
    0.06
    Activations Density 0.000%

    No Known Activations