© 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. 91243
    Prev
    Next
    INDEX
    Explanations

    Expectations

    np_max-act · gemini-2.0-flash

    financial metrics and indicators related to earnings reports.

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

    The neuron detects words and phrases that signal a comparison of actual results against forecasts (e.g., “better than expected,” “beat expectations,” “forecast”).

    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
     quadratic
    -0.07
     incident
    -0.07
    ्वत
    -0.07
    ματο
    -0.07
     another
    -0.06
    ян
    -0.06
     Ev
    -0.06
    ycling
    -0.06
    tested
    -0.06
     affects
    -0.06
    POSITIVE LOGITS
     touted
    0.07
     Wants
    0.07
     illegally
    0.06
    QtCore
    0.06
    DetailView
    0.06
    824
    0.06
    (dto
    0.06
    İS
    0.06
     destructive
    0.06
     contention
    0.06
    Activations Density 0.007%

    No Known Activations