© 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 EvalsExportsinterp-engineNEWAPI 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. 57607
    Prev
    Next
    INDEX
    Explanations

    resort to

    np_max-act · gemini-2.0-flash

    This neuron activates on the phrase “resort to,” detecting when the text uses that fallback expression.

    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
    ustainability
    -0.07
    /he
    -0.07
     Gä
    -0.07
    \v
    -0.06
     Bonnie
    -0.06
    /New
    -0.06
     FRE
    -0.06
    Title
    -0.06
     Fre
    -0.06
     Edwin
    -0.06
    POSITIVE LOGITS
     resort
    0.11
     Resort
    0.11
     resorts
    0.10
     Resorts
    0.08
     effects
    0.07
    OR
    0.07
    resas
    0.07
     método
    0.07
     Filed
    0.07
    rp
    0.07
    Activations Density 0.005%

    No Known Activations