© 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. 91172
    Prev
    Next
    INDEX
    Explanations

    "to be" verb forms

    np_max-act · gemini-2.0-flash

    content related to business strategies and planning.

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

    The neuron selectively activates on floating-point number tokens (i.e. numeric strings containing a decimal point).

    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
     Quad
    -0.07
     modifying
    -0.07
    langle
    -0.07
    anye
    -0.06
     Cindy
    -0.06
    cloak
    -0.06
     Europ
    -0.06
     `<
    -0.06
    hoe
    -0.06
    white
    -0.06
    POSITIVE LOGITS
    ’m
    0.08
     be
    0.08
     been
    0.07
     ARE
    0.07
     is
    0.07
    えた
    0.07
     aren
    0.07
    erosis
    0.07
     erupted
    0.07
     wasn
    0.07
    Activations Density 0.035%

    No Known Activations