© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43303
    Prev
    Next
    INDEX
    Explanations

    sigma

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “sigma” in the context of sigma receptors (e.g., “sigma receptor,” “sigma 1 receptor”).

    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
     Faster
    -0.06
    .handlers
    -0.06
     createStackNavigator
    -0.06
     inhibitor
    -0.06
     discounts
    -0.06
     screenshot
    -0.06
     mesaj
    -0.06
     screaming
    -0.06
     setInput
    -0.06
     překlad
    -0.06
    POSITIVE LOGITS
     SEA
    0.06
     scale
    0.06
            
    0.06
     worlds
    0.06
     lie
    0.06
     refin
    0.06
     resolving
    0.06
    _/
    0.06
    Door
    0.06
     Change
    0.06
    Activations Density 0.002%

    No Known Activations