© 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. 7290
    Prev
    Next
    INDEX
    Explanations

    "actory" suffix

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the term “refractory” (i.e. treatment-resistant) in medical contexts.

    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
    论
    -0.07
     Mathematics
    -0.07
     cruise
    -0.06
    네
    -0.06
     dives
    -0.06
                                                    ↵
    -0.06
     landing
    -0.06
     four
    -0.06
    quiz
    -0.06
    (ans
    -0.06
    POSITIVE LOGITS
    naires
    0.06
     IPV
    0.06
     těž
    0.06
    }*
    0.06
     Jeg
    0.06
     Youtube
    0.06
     зависим
    0.06
     thậm
    0.06
    .Schema
    0.06
     mild
    0.06
    Activations Density 0.005%

    No Known Activations