© 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. 38689
    Prev
    Next
    INDEX
    Explanations

    Unfortunately

    np_max-act · gemini-2.0-flash

    financial figures and data related to corporate spending.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on the word “Unfortunately” (i.e. it’s spotting occurrences of a negative/disclaimer word at the start of a clause).

    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
     tyres
    -0.07
     Zhao
    -0.07
     behaves
    -0.07
     bulk
    -0.06
     Dry
    -0.06
     seven
    -0.06
     Yam
    -0.06
     basic
    -0.06
     BP
    -0.06
     Maur
    -0.06
    POSITIVE LOGITS
    Unfortunately
    0.11
     Unfortunately
    0.11
     unfortunately
    0.09
     قتل
    0.08
    fortunately
    0.08
     downhill
    0.07
    ßerdem
    0.07
    мент
    0.07
     fecha
    0.07
    lehem
    0.07
    Activations Density 0.009%

    No Known Activations