© 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. 43314
    Prev
    Next
    INDEX
    Explanations

    quantum physics and oscillation

    np_max-act · gemini-2.0-flash

    This neuron activates on technical physics terms related to “quantum” phenomena, especially words containing the root “quant” (e.g. quantum, quantization) and “point” as in “point contacts.”

    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
    _USED
    -0.08
    PFN
    -0.07
    single
    -0.07
     Singh
    -0.07
    気
    -0.06
     uptime
    -0.06
    _messages
    -0.06
    μος
    -0.06
    -labelled
    -0.06
     singled
    -0.06
    POSITIVE LOGITS
     دول
    0.07
     NGX
    0.06
    _Core
    0.06
     psik
    0.06
    BAT
    0.06
     mockery
    0.06
    _HISTORY
    0.06
         
    0.06
    ritt
    0.06
    957
    0.05
    Activations Density 0.011%

    No Known Activations