© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125130
    Prev
    Next
    INDEX
    Explanations

    resist

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of “resist” (and related resistance/temptation 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
     simpler
    -0.08
    ยอด
    -0.07
     злоч
    -0.07
     leaks
    -0.07
     yarar
    -0.07
     мире
    -0.07
    kili
    -0.06
     chaos
    -0.06
     fullname
    -0.06
     Bronx
    -0.06
    POSITIVE LOGITS
     resisted
    0.09
     resist
    0.08
     resisting
    0.07
     irresist
    0.07
     --------------------------------
    0.07
     APPRO
    0.06
    '],↵
    0.06
    ß
    0.06
    	NdrFc
    0.06
    PRICE
    0.06
    Activations Density 0.004%

    No Known Activations