© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6789
    Prev
    Next
    INDEX
    Explanations

    spy

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of spying and espionage (e.g., “spy,” “spying,” “espionage”).

    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
     transitioning
    -0.07
    REDIENT
    -0.07
     fragmentation
    -0.07
    ATER
    -0.07
    ATIONS
    -0.07
    Cake
    -0.06
    ">↵↵↵
    -0.06
     CONDITIONS
    -0.06
     ukon
    -0.06
    GLOSS
    -0.06
    POSITIVE LOGITS
     spy
    0.14
     Spy
    0.11
     spying
    0.10
    Spy
    0.09
     spies
    0.08
    spy
    0.08
     Voy
    0.07
     Experts
    0.07
     voy
    0.07
     xmlns
    0.07
    Activations Density 0.003%

    No Known Activations